#include "html.h"
#include "HTMLControl.h"
#include "sgml.h"
#include "cmp_nocase.h"
#ifndef nelems
#define nelems(array) (sizeof(array) / sizeof((array)[0]))
#endif
enum {
NOT_A_TAG,
START_TAG, BLOCK_START_TAG,
END_TAG, BLOCK_END_TAG,
NON_CONTAINER_TAG
};
/* ------------------------------------------------------------------------- */
/*
* Effectively, this method simply invokes "yylex2()", but it does some
* postprocessing on PCDATA tokens that would be difficult to do in "yylex2()".
*/
int
HTMLControl::yylex(yy_HTMLParser_stype *value_return)
{
for (;;) { // Notice the "return" at the end of the body!
int token, tag_type;
if (next_token == EOF) {
token = yylex2(value_return, &tag_type);
} else {
token = next_token;
*value_return = next_token_value;
tag_type = next_token_tag_type;
next_token = EOF;
}
/*
* Switch on/off "literal mode" on "" and "
".
*/
if (token == PRE) {
literal_mode = true;
/*
* Swallow '\n' immediately following "".
*/
if (next_token == EOF) {
next_token = yylex2(&next_token_value, &next_token_tag_type);
}
if (next_token == PCDATA) {
string &s(*next_token_value.strinG);
if (!s.empty() && s[0] == '\n') s.erase(0, 1);
}
}
if (token == END_PRE) literal_mode = false;
if (token == PCDATA) {
/*
* In order to post-process the PCDATA token, we need to look ahead one
* token...
*/
if (next_token == EOF) {
next_token = yylex2(&next_token_value, &next_token_tag_type);
}
/*
* Erase " '\n' { ' ' } " immediately before "".
*/
if (next_token == END_PRE) {
string &s(*value_return->strinG);
string::size_type x = s.length();
while (x > 0 && s[x - 1] == ' ') --x;
if (x > 0 && s[x - 1] == '\n') s.erase(x - 1, string::npos);
} else
/*
* Erase whitespace before end tag or block start tag.
*/
if (!literal_mode && (
next_token_tag_type == END_TAG ||
next_token_tag_type == BLOCK_END_TAG ||
next_token_tag_type == BLOCK_START_TAG
)) {
string &s(*value_return->strinG);
string::size_type x = s.length();
while (x > 0 && isspace(s[x - 1])) --x;
s.erase(x, string::npos);
}
/*
* Collate sequences of whitespace, if not in "literal mode".
*/
if (!literal_mode) {
string &s(*value_return->strinG);
// bool whitespace_only = true;
for (string::size_type x = 0; x < s.length(); ++x) {
if (isspace(s[x])) {
string::size_type y;
for (y = x + 1; y < s.length() && isspace(s[y]); ++y);
s.replace(x, y - x, " ");
} else {
// whitespace_only = false;
}
}
if (s.empty()) { delete value_return->strinG; continue; }
}
}
/*
* Erase whitespace after start tag or block end tag, if not in "literal
* mode".
*/
if (!literal_mode && (
(
tag_type == START_TAG ||
tag_type == BLOCK_START_TAG ||
tag_type == BLOCK_END_TAG ||
token == BR ||
token == HR
) &&
token != SCRIPT && token != STYLE
)) {
if (next_token == EOF) {
next_token = yylex2(&next_token_value, &next_token_tag_type);
}
if (next_token == PCDATA) {
string &s(*next_token_value.strinG);
string::size_type x;
for (x = 0; x < s.length() && isspace(s[x]); ++x);
if (x > 0) s.erase(0, x);
if (s.empty()) {
delete next_token_value.strinG;
next_token = EOF;
}
}
}
return token;
}
}
/* ------------------------------------------------------------------------- */
/*
* Keep this array sorted alphabetically!
*/
static const struct TextToIntP {
char name[11];
char block_tag;
const int *start_tag_code;
const int *end_tag_code;
} tag_names[] = {
#define pack1(tag) { #tag, 0, &HTMLParser::tag, 0 }
#define pack2(tag) { #tag, 0, &HTMLParser::tag, &HTMLParser::END_##tag }
#define pack3(tag) { #tag, 1, &HTMLParser::tag, &HTMLParser::END_##tag }
pack2(A),
pack3(ADDRESS),
pack2(APPLET),
pack1(AREA),
pack2(B),
pack1(BASE),
pack1(BASEFONT),
pack2(BIG),
pack3(BLOCKQUOTE),
pack3(BODY),
pack1(BR),
pack3(CAPTION),
pack3(CENTER),
pack3(CITE),
pack2(CODE),
pack3(DD),
pack2(DFN),
pack3(DIR),
pack3(DIV),
pack3(DL),
pack3(DT),
pack2(EM),
pack2(FONT),
pack3(FORM),
pack3(H1),
pack3(H2),
pack3(H3),
pack3(H4),
pack3(H5),
pack3(H6),
pack3(HEAD),
pack1(HR),
pack3(HTML),
pack2(I),
pack1(IMG),
pack1(INPUT),
pack1(ISINDEX),
pack2(KBD),
pack3(LI),
pack1(LINK),
pack2(MAP),
pack3(MENU),
pack1(META),
pack2(NOBR),
pack3(OL),
pack3(OPTION),
pack3(P),
pack1(PARAM),
pack3(PRE),
pack2(SAMP),
pack3(SCRIPT),
pack2(SELECT),
pack2(SMALL),
pack2(STRIKE),
pack2(STRONG),
pack3(STYLE),
pack2(SUB),
pack2(SUP),
pack3(TABLE),
pack3(TD),
pack2(TEXTAREA),
pack3(TH),
pack3(TITLE),
pack3(TR),
pack2(TT),
pack2(U),
pack3(UL),
pack2(VAR),
#undef pack
};
/* ------------------------------------------------------------------------- */
int
HTMLControl::yylex2(yy_HTMLParser_stype *value_return, int *tag_type_return)
{
int c;
*tag_type_return = NOT_A_TAG;
for (;;) { // Notice the "return" at the end of this loop.
/*
* Get the first character of the token.
*/
c = get_char();
if (c == EOF) return EOF;
if (c == '<') {
/*
* Examine the first character of the tag.
*/
c = get_char();
if (c == '!') {
c = get_char();
if (c == '-') {
c = get_char();
if (c != '-') return SCAN_ERROR;
/*
* This is a comment... skip it!
*
*
*
*
*
* EXTENSION: Allow "-->" as the terminator of a multi-line comment.
*/
int state = 0;
do {
c = get_char();
if (c == EOF) return SCAN_ERROR;
switch (state) {
case 0: if (c == '-') state = 1; break;
case 1: state = c == '-' ? 2 : 0; break;
case 2: state = c == '>' ? 3 : c == '-' ? 2 : 0; break;
}
} while (state != 3);
continue; // Start over
}
/*
* Scan "" tag.
*/
if (!isalpha(c)) return SCAN_ERROR;
string tag_name(1, '!');
tag_name += c;
for (;;) {
c = get_char();
if (!isalnum(c) && c != '-') break;
tag_name += c;
}
if (cmp_nocase(tag_name, "!DOCTYPE") != 0) return SCAN_ERROR;
while (c != '>') {
c = get_char();
if (c == EOF) return SCAN_ERROR;
// Let newline not close the DOCTYPE tag - Arno
}
return DOCTYPE;
}
if (c == '/' || isalpha(c) || c == '_') {
string tag_name;
bool is_end_tag = false;
if (c == '/') { is_end_tag = true; c = get_char(); }
if (!isalpha(c) && c != '_') return SCAN_ERROR;
tag_name += c;
for (;;) {
c = get_char();
if (!isalnum(c) && c != '-' && c != '_' && c != ':') break;
// Tolerate colons in tags for MS-Word's sake - Arno
tag_name += c;
}
while (isspace(c)) c = get_char();
/*
* Scan tag attributes (only for opening tags). Create the
* "tag_attributes" only on demand; this saves a lot of overhead.
*/
auto_ptr > tag_attributes;
if (!is_end_tag) {
while (isalpha(c) || c == '_') {
TagAttribute attribute;
/*
* Scan attribute name.
*/
attribute.first = c;
for (;;) {
c = get_char();
if (!isalpha(c) && c != '-' && c != '_' && c != ':') break;
// Same as in line 352 - Arno
attribute.first += c;
}
while (isspace(c)) c = get_char(); // Skip WS after attribute name
/*
* Scan (optional) attribute value.
*/
if (c == '=') {
c = get_char();
while (isspace(c)) c = get_char();
if (c == '"' || c == '\'') {
int closing_quote = c; // Same as opening quote!
for (;;) {
c = get_char();
if (c == EOF) return SCAN_ERROR;
// Accept multiple-line elements - Arno
if (c == closing_quote) break;
/*
* Do *not* interpret "ä" and consorts here! This
* would ruin tag attributes like "HREF=hhh?a=1&b=2".
*/
attribute.second += c;
}
c = get_char(); // Get next char after closing quote.
} else
while (c != '>' && (unsigned char) c > (unsigned char) ' ') {
// This is for non-ACSII chars - Arno
if (c == EOF) return SCAN_ERROR;
// Same as in line 390
attribute.second += c;
c = get_char();
}
while (isspace(c)) c = get_char(); // Skip WS after attr value
}
/*
* Store the attribute.
*/
if (!tag_attributes.get()) {
tag_attributes.reset(new list);
}
tag_attributes->push_back(attribute);
}
}
// accept XHTML tags like
- Alexander Solovey
if (c != '>') {
if ( c == '/' ) {
c = get_char();
if (c != '>') {
return SCAN_ERROR;
}
}
else {
return SCAN_ERROR;
}
}
if (debug_scanner) {
std::cerr << "Scanned tag \"<" << (is_end_tag ? "/" : "") << tag_name;
if (!is_end_tag && tag_attributes.get()) {
const list &ta(*tag_attributes);
list::const_iterator j;
for (j = ta.begin(); j != ta.end(); ++j) {
std::cerr << " " << (*j).first << "=\"" << (*j).second << "\"";
}
}
std::cerr << ">\"" << std::endl;
}
/*
* Look up the tag in the table of recognized tags.
*/
static int (*const f)(const char *, const char *) = cmp_nocase;
const TextToIntP *tag = (const TextToIntP *) bsearch(
tag_name.c_str(),
tag_names, nelems(tag_names), sizeof(TextToIntP),
(int (*)(const void *, const void *)) f
);
if (tag == NULL) { /* EXTENSION: Swallow unknown tags. */
if (debug_scanner) {
std::cerr << "Tag unknown -- swallowed." << std::endl;
}
continue;
}
/*
* Return the BISON token code for the tag.
*/
if (is_end_tag) {
if (!tag->end_tag_code) {
if (debug_scanner) {
std::cerr << "Non-container end tag scanned." << std::endl;
}
continue;
}
*tag_type_return = tag->block_tag ? BLOCK_END_TAG : END_TAG;
return *tag->end_tag_code;
} else {
*tag_type_return = (
!tag->end_tag_code ? NON_CONTAINER_TAG :
tag->block_tag ? BLOCK_START_TAG : START_TAG
);
value_return->tag_attributes = tag_attributes.release();
return *tag->start_tag_code;
}
}
/*
* EXTENSION: This tag did not match "= (unsigned char) ' ') {
// Same as in line 402
string *s = value_return->strinG = new string;
while (c != EOF) {
/*
* Accept literal '<' in some cases.
*/
if (c == '<') {
int c2;
unget_char(c2 = get_char());
if (c2 == '!' || c2 == '/' || isalpha(c2)) { unget_char(c); break; }
}
*s += c;
c = get_char();
}
replace_sgml_entities(s); // Replace "ä" and consorts.
/*
* Swallow empty PCDATAs.
*/
if (s->empty()) { delete s; continue; }
if (debug_scanner) std::cerr << "Scanned PCDATA \"" << *s << "\"" << std::endl;
return PCDATA;
}
return SCAN_ERROR;
}
}
/* ------------------------------------------------------------------------- */
bool
HTMLControl::read_cdata(const char *terminal, string *value_return)
{
string &s(*value_return);
int c;
int state = 0;
for (;;) {
c = get_char();
if (c == EOF) return false;
if (toupper(c) == terminal[state]) {
state++;
if (terminal[state] == '\0') {
// s.erase(s.length() - state);
// caused core dump on empty STYLE and SCRIPT elements - Johannes Geiger
s.erase(s.length() - state + 1);
return true;
}
} else {
state = 0;
}
s += c;
}
}
/* ------------------------------------------------------------------------- */
int
HTMLControl::get_char()
{
if (number_of_ungotten_chars > 0) {
return ungotten_chars[--number_of_ungotten_chars];
}
int c = is.get();
while (c == '\r') c = is.get();
if (c == EOF) {
;
} else
if (c == '\n') {
current_line++;
current_column = 0;
} else {
current_column++;
}
return c;
}
/* ------------------------------------------------------------------------- */
void
HTMLControl::unget_char(int c)
{
if (number_of_ungotten_chars == nelems(ungotten_chars)) {
yyerror("Too many chars ungotten");
return;
}
ungotten_chars[number_of_ungotten_chars++] = c;
}
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/HTMLControl.h 0100644 0000000 0000000 00000005222 07760112171 014571 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer
* Dates and reasons of modifications:
* Thu Oct 4 21:25:07 CEST 2001: ported to g++ 3.0
* Wed Jul 2 22:01:12 CEST 2003: ported to g++ 3.3
*/
/***************************************************************************/
#ifndef __HTMLControl_h_INCLUDED__ /* { */
#define __HTMLControl_h_INCLUDED__
/* ------------------------------------------------------------------------- */
#include "HTMLParser.h"
#include "urlistream.h"
#include
using std::istream;
/* ------------------------------------------------------------------------- */
class HTMLControl : public HTMLParser {
public:
HTMLControl(urlistream &is_, bool debug_scanner_, bool debug_parser_) :
HTMLParser(),
current_line(1),
current_column(0),
literal_mode(false),
next_token(EOF),
debug_scanner(debug_scanner_),
is(is_),
number_of_ungotten_chars(0)
{ yydebug = debug_parser_; }
int current_line;
int current_column;
private:
/*
* Implementing virtual methods of "HTMLParser".
*/
/*virtual*/ int yylex(yy_HTMLParser_stype *value_return);
/*virtual*/ bool read_cdata(const char *terminal, string *value_return);
/*
* Helpers.
*/
int yylex2(yy_HTMLParser_stype *value_return, int *tag_type_return);
bool literal_mode;
int next_token;
yy_HTMLParser_stype next_token_value;
int next_token_tag_type;
int get_char();
void unget_char(int);
bool debug_scanner;
urlistream &is;
int ungotten_chars[5];
int number_of_ungotten_chars;
};
/* ------------------------------------------------------------------------- */
#endif /* } */
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/HTMLParser.C 0100644 0000000 0000000 00000337463 07760112171 014357 0 ustar root root #define YY_HTMLParser_h_included
/* A Bison parser, made from HTMLParser.y */
#line 1 "/usr/local/lib/bison.cc"
/* -*-C-*- Note some compilers choke on comments on `#line' lines. */
/* Skeleton output parser for bison,
Copyright (C) 1984, 1989, 1990 Bob Corbett and Richard Stallman
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 1, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
/* HEADER SECTION */
#ifndef _MSDOS
#ifdef MSDOS
#define _MSDOS
#endif
#endif
/* turboc */
#ifdef __MSDOS__
#ifndef _MSDOS
#define _MSDOS
#endif
#endif
#ifndef alloca
#ifdef __GNUC__
#define alloca __builtin_alloca
#else /* not GNU C. */
#if (!defined (__STDC__) && defined (sparc)) || defined (__sparc__) || defined (__sparc)
#include
#else /* not sparc */
#if defined (_MSDOS)
#include
#ifndef __TURBOC__
/* MS C runtime lib */
#define alloca _alloca
#endif
#else /* not MSDOS, or __TURBOC__ */
#if defined(_AIX)
#include
#pragma alloca
#endif /* not _AIX */
#endif /* not MSDOS, or __TURBOC__ */
#endif /* not sparc. */
#endif /* not GNU C. */
#endif /* alloca not defined. */
#ifdef c_plusplus
#ifndef __cplusplus
#define __cplusplus
#endif
#endif
#ifdef __cplusplus
#ifndef YY_USE_CLASS
#define YY_USE_CLASS
#endif
#else
#ifndef __STDC__
#define const
#endif
#endif
#include
#define YYBISON 1
/* #line 70 "/usr/local/lib/bison.cc" */
#define YY_HTMLParser_PURE
#define YY_HTMLParser_DEBUG 1
#line 40 "HTMLParser.y"
/* ------------------------------------------------------------------------- */
#ident "$Id: HTMLParser.y,v 1.14 1999/10/26 10:56:55 arno Exp $"
#include "html.h"
#include "HTMLParser.h"
// MIPS machines don't have "alloca()", so disable stack realloc'ing.
#ifdef mips
#define yyoverflow yyerror("parser stack overflow"), (void)
#endif
/* ------------------------------------------------------------------------- */
#define YY_HTMLParser_LEX_BODY = 0
#define YY_HTMLParser_ERROR_BODY = 0
#define YY_HTMLParser_MEMBERS \
virtual ~HTMLParser(); \
virtual void process(const Document &) = 0;\
virtual bool read_cdata(const char *terminal, string *) = 0;\
int list_nesting;
#define YY_HTMLParser_CONSTRUCTOR_INIT : list_nesting(0)
#line 69 "HTMLParser.y"
typedef union {
Document *document;
Element *element;
list > *element_list;
PCData *pcdata;
string *strinG;
list *tag_attributes;
int inT;
list > *table_rows;
list > *table_cells;
ListItem *list_item;
list > *list_items;
Caption *caption;
Heading *heading;
list > *option_list;
Option *option;
DefinitionList *definition_list;
list > *definition_list_item_list;
TermName *term_name;
TermDefinition *term_definition;
Preformatted *preformatted;
Address *address;
list > > *tag_attributes_list;
} yy_HTMLParser_stype;
#define YY_HTMLParser_STYPE yy_HTMLParser_stype
#line 70 "/usr/local/lib/bison.cc"
/* %{ and %header{ and %union, during decl */
#define YY_HTMLParser_BISON 1
#ifndef YY_HTMLParser_COMPATIBILITY
#ifndef YY_USE_CLASS
#define YY_HTMLParser_COMPATIBILITY 1
#else
#define YY_HTMLParser_COMPATIBILITY 0
#endif
#endif
#if YY_HTMLParser_COMPATIBILITY != 0
/* backward compatibility */
#ifdef YYLTYPE
#ifndef YY_HTMLParser_LTYPE
#define YY_HTMLParser_LTYPE YYLTYPE
#endif
#endif
#ifdef YYSTYPE
#ifndef YY_HTMLParser_STYPE
#define YY_HTMLParser_STYPE YYSTYPE
#endif
#endif
#ifdef YYDEBUG
#ifndef YY_HTMLParser_DEBUG
#define YY_HTMLParser_DEBUG YYDEBUG
#endif
#endif
#ifdef YY_HTMLParser_STYPE
#ifndef yystype
#define yystype YY_HTMLParser_STYPE
#endif
#endif
#endif
#ifndef YY_HTMLParser_PURE
/* #line 105 "/usr/local/lib/bison.cc" */
#line 105 "/usr/local/lib/bison.cc"
/* YY_HTMLParser_PURE */
#endif
/* section apres lecture def, avant lecture grammaire S2 */
/* #line 109 "/usr/local/lib/bison.cc" */
#line 109 "/usr/local/lib/bison.cc"
/* prefix */
#ifndef YY_HTMLParser_DEBUG
/* #line 111 "/usr/local/lib/bison.cc" */
#line 111 "/usr/local/lib/bison.cc"
/* YY_HTMLParser_DEBUG */
#endif
#ifndef YY_HTMLParser_LSP_NEEDED
/* #line 116 "/usr/local/lib/bison.cc" */
#line 116 "/usr/local/lib/bison.cc"
/* YY_HTMLParser_LSP_NEEDED*/
#endif
/* DEFAULT LTYPE*/
#ifdef YY_HTMLParser_LSP_NEEDED
#ifndef YY_HTMLParser_LTYPE
typedef
struct yyltype
{
int timestamp;
int first_line;
int first_column;
int last_line;
int last_column;
char *text;
}
yyltype;
#define YY_HTMLParser_LTYPE yyltype
#endif
#endif
/* DEFAULT STYPE*/
/* We used to use `unsigned long' as YY_HTMLParser_STYPE on MSDOS,
but it seems better to be consistent.
Most programs should declare their own type anyway. */
#ifndef YY_HTMLParser_STYPE
#define YY_HTMLParser_STYPE int
#endif
/* DEFAULT MISCELANEOUS */
#ifndef YY_HTMLParser_PARSE
#define YY_HTMLParser_PARSE yyparse
#endif
#ifndef YY_HTMLParser_LEX
#define YY_HTMLParser_LEX yylex
#endif
#ifndef YY_HTMLParser_LVAL
#define YY_HTMLParser_LVAL yylval
#endif
#ifndef YY_HTMLParser_LLOC
#define YY_HTMLParser_LLOC yylloc
#endif
#ifndef YY_HTMLParser_CHAR
#define YY_HTMLParser_CHAR yychar
#endif
#ifndef YY_HTMLParser_NERRS
#define YY_HTMLParser_NERRS yynerrs
#endif
#ifndef YY_HTMLParser_DEBUG_FLAG
#define YY_HTMLParser_DEBUG_FLAG yydebug
#endif
#ifndef YY_HTMLParser_ERROR
#define YY_HTMLParser_ERROR yyerror
#endif
#ifndef YY_HTMLParser_PARSE_PARAM
#ifndef __STDC__
#ifndef __cplusplus
#ifndef YY_USE_CLASS
#define YY_HTMLParser_PARSE_PARAM
#ifndef YY_HTMLParser_PARSE_PARAM_DEF
#define YY_HTMLParser_PARSE_PARAM_DEF
#endif
#endif
#endif
#endif
#ifndef YY_HTMLParser_PARSE_PARAM
#define YY_HTMLParser_PARSE_PARAM void
#endif
#endif
/* TOKEN C */
#if YY_HTMLParser_COMPATIBILITY != 0
/* backward compatibility */
#ifdef YY_HTMLParser_LTYPE
#ifndef YYLTYPE
#define YYLTYPE YY_HTMLParser_LTYPE
#else
/* WARNING obsolete !!! user defined YYLTYPE not reported into generated header */
#endif
#endif
#ifndef YYSTYPE
#define YYSTYPE YY_HTMLParser_STYPE
#else
/* WARNING obsolete !!! user defined YYSTYPE not reported into generated header */
#endif
#ifdef YY_HTMLParser_PURE
#ifndef YYPURE
#define YYPURE YY_HTMLParser_PURE
#endif
#endif
#ifdef YY_HTMLParser_DEBUG
#ifndef YYDEBUG
#define YYDEBUG YY_HTMLParser_DEBUG
#endif
#endif
#ifndef YY_HTMLParser_ERROR_VERBOSE
#ifdef YYERROR_VERBOSE
#define YY_HTMLParser_ERROR_VERBOSE YYERROR_VERBOSE
#endif
#endif
#ifndef YY_HTMLParser_LSP_NEEDED
#ifdef YYLSP_NEEDED
#define YY_HTMLParser_LSP_NEEDED YYLSP_NEEDED
#endif
#endif
/* #line 223 "/usr/local/lib/bison.cc" */
#define DOCTYPE 258
#define PCDATA 259
#define SCAN_ERROR 260
#define A 261
#define ADDRESS 262
#define APPLET 263
#define AREA 264
#define B 265
#define BASE 266
#define BASEFONT 267
#define BIG 268
#define BLOCKQUOTE 269
#define BODY 270
#define BR 271
#define CAPTION 272
#define CENTER 273
#define CITE 274
#define CODE 275
#define DD 276
#define DFN 277
#define DIR 278
#define DIV 279
#define DL 280
#define DT 281
#define EM 282
#define FONT 283
#define FORM 284
#define H1 285
#define H2 286
#define H3 287
#define H4 288
#define H5 289
#define H6 290
#define HEAD 291
#define HR 292
#define HTML 293
#define I 294
#define IMG 295
#define INPUT 296
#define ISINDEX 297
#define KBD 298
#define LI 299
#define LINK 300
#define MAP 301
#define MENU 302
#define META 303
#define NOBR 304
#define OL 305
#define OPTION 306
#define P 307
#define PARAM 308
#define PRE 309
#define SAMP 310
#define SCRIPT 311
#define SELECT 312
#define SMALL 313
#define STRIKE 314
#define STRONG 315
#define STYLE 316
#define SUB 317
#define SUP 318
#define TABLE 319
#define TD 320
#define TEXTAREA 321
#define TH 322
#define TITLE 323
#define TR 324
#define TT 325
#define U 326
#define UL 327
#define VAR 328
#define END_A 329
#define END_ADDRESS 330
#define END_APPLET 331
#define END_B 332
#define END_BIG 333
#define END_BLOCKQUOTE 334
#define END_BODY 335
#define END_CAPTION 336
#define END_CENTER 337
#define END_CITE 338
#define END_CODE 339
#define END_DD 340
#define END_DFN 341
#define END_DIR 342
#define END_DIV 343
#define END_DL 344
#define END_DT 345
#define END_EM 346
#define END_FONT 347
#define END_FORM 348
#define END_H1 349
#define END_H2 350
#define END_H3 351
#define END_H4 352
#define END_H5 353
#define END_H6 354
#define END_HEAD 355
#define END_HTML 356
#define END_I 357
#define END_KBD 358
#define END_LI 359
#define END_MAP 360
#define END_MENU 361
#define END_NOBR 362
#define END_OL 363
#define END_OPTION 364
#define END_P 365
#define END_PRE 366
#define END_SAMP 367
#define END_SCRIPT 368
#define END_SELECT 369
#define END_SMALL 370
#define END_STRIKE 371
#define END_STRONG 372
#define END_STYLE 373
#define END_SUB 374
#define END_SUP 375
#define END_TABLE 376
#define END_TD 377
#define END_TEXTAREA 378
#define END_TH 379
#define END_TITLE 380
#define END_TR 381
#define END_TT 382
#define END_U 383
#define END_UL 384
#define END_VAR 385
#line 223 "/usr/local/lib/bison.cc"
/* #defines tokens */
#else
/* CLASS */
#ifndef YY_HTMLParser_CLASS
#define YY_HTMLParser_CLASS HTMLParser
#endif
#ifndef YY_HTMLParser_INHERIT
#define YY_HTMLParser_INHERIT
#endif
#ifndef YY_HTMLParser_MEMBERS
#define YY_HTMLParser_MEMBERS
#endif
#ifndef YY_HTMLParser_LEX_BODY
#define YY_HTMLParser_LEX_BODY
#endif
#ifndef YY_HTMLParser_ERROR_BODY
#define YY_HTMLParser_ERROR_BODY
#endif
#ifndef YY_HTMLParser_CONSTRUCTOR_PARAM
#define YY_HTMLParser_CONSTRUCTOR_PARAM
#endif
#ifndef YY_HTMLParser_CONSTRUCTOR_CODE
#define YY_HTMLParser_CONSTRUCTOR_CODE
#endif
#ifndef YY_HTMLParser_CONSTRUCTOR_INIT
#define YY_HTMLParser_CONSTRUCTOR_INIT
#endif
class YY_HTMLParser_CLASS YY_HTMLParser_INHERIT
{
public: /* static const int token ... */
/* #line 254 "/usr/local/lib/bison.cc" */
static const int DOCTYPE;
static const int PCDATA;
static const int SCAN_ERROR;
static const int A;
static const int ADDRESS;
static const int APPLET;
static const int AREA;
static const int B;
static const int BASE;
static const int BASEFONT;
static const int BIG;
static const int BLOCKQUOTE;
static const int BODY;
static const int BR;
static const int CAPTION;
static const int CENTER;
static const int CITE;
static const int CODE;
static const int DD;
static const int DFN;
static const int DIR;
static const int DIV;
static const int DL;
static const int DT;
static const int EM;
static const int FONT;
static const int FORM;
static const int H1;
static const int H2;
static const int H3;
static const int H4;
static const int H5;
static const int H6;
static const int HEAD;
static const int HR;
static const int HTML;
static const int I;
static const int IMG;
static const int INPUT;
static const int ISINDEX;
static const int KBD;
static const int LI;
static const int LINK;
static const int MAP;
static const int MENU;
static const int META;
static const int NOBR;
static const int OL;
static const int OPTION;
static const int P;
static const int PARAM;
static const int PRE;
static const int SAMP;
static const int SCRIPT;
static const int SELECT;
static const int SMALL;
static const int STRIKE;
static const int STRONG;
static const int STYLE;
static const int SUB;
static const int SUP;
static const int TABLE;
static const int TD;
static const int TEXTAREA;
static const int TH;
static const int TITLE;
static const int TR;
static const int TT;
static const int U;
static const int UL;
static const int VAR;
static const int END_A;
static const int END_ADDRESS;
static const int END_APPLET;
static const int END_B;
static const int END_BIG;
static const int END_BLOCKQUOTE;
static const int END_BODY;
static const int END_CAPTION;
static const int END_CENTER;
static const int END_CITE;
static const int END_CODE;
static const int END_DD;
static const int END_DFN;
static const int END_DIR;
static const int END_DIV;
static const int END_DL;
static const int END_DT;
static const int END_EM;
static const int END_FONT;
static const int END_FORM;
static const int END_H1;
static const int END_H2;
static const int END_H3;
static const int END_H4;
static const int END_H5;
static const int END_H6;
static const int END_HEAD;
static const int END_HTML;
static const int END_I;
static const int END_KBD;
static const int END_LI;
static const int END_MAP;
static const int END_MENU;
static const int END_NOBR;
static const int END_OL;
static const int END_OPTION;
static const int END_P;
static const int END_PRE;
static const int END_SAMP;
static const int END_SCRIPT;
static const int END_SELECT;
static const int END_SMALL;
static const int END_STRIKE;
static const int END_STRONG;
static const int END_STYLE;
static const int END_SUB;
static const int END_SUP;
static const int END_TABLE;
static const int END_TD;
static const int END_TEXTAREA;
static const int END_TH;
static const int END_TITLE;
static const int END_TR;
static const int END_TT;
static const int END_U;
static const int END_UL;
static const int END_VAR;
#line 254 "/usr/local/lib/bison.cc"
/* decl const */
public:
int YY_HTMLParser_PARSE (YY_HTMLParser_PARSE_PARAM);
virtual void YY_HTMLParser_ERROR(char *msg) YY_HTMLParser_ERROR_BODY;
#ifdef YY_HTMLParser_PURE
#ifdef YY_HTMLParser_LSP_NEEDED
virtual int YY_HTMLParser_LEX (YY_HTMLParser_STYPE *YY_HTMLParser_LVAL,YY_HTMLParser_LTYPE *YY_HTMLParser_LLOC) YY_HTMLParser_LEX_BODY;
#else
virtual int YY_HTMLParser_LEX (YY_HTMLParser_STYPE *YY_HTMLParser_LVAL) YY_HTMLParser_LEX_BODY;
#endif
#else
virtual int YY_HTMLParser_LEX() YY_HTMLParser_LEX_BODY;
YY_HTMLParser_STYPE YY_HTMLParser_LVAL;
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE YY_HTMLParser_LLOC;
#endif
int YY_HTMLParser_NERRS;
int YY_HTMLParser_CHAR;
#endif
#if YY_HTMLParser_DEBUG != 0
int YY_HTMLParser_DEBUG_FLAG; /* nonzero means print parse trace */
#endif
public:
YY_HTMLParser_CLASS(YY_HTMLParser_CONSTRUCTOR_PARAM);
public:
YY_HTMLParser_MEMBERS
};
/* other declare folow */
/* #line 282 "/usr/local/lib/bison.cc" */
const int YY_HTMLParser_CLASS::DOCTYPE=258;
const int YY_HTMLParser_CLASS::PCDATA=259;
const int YY_HTMLParser_CLASS::SCAN_ERROR=260;
const int YY_HTMLParser_CLASS::A=261;
const int YY_HTMLParser_CLASS::ADDRESS=262;
const int YY_HTMLParser_CLASS::APPLET=263;
const int YY_HTMLParser_CLASS::AREA=264;
const int YY_HTMLParser_CLASS::B=265;
const int YY_HTMLParser_CLASS::BASE=266;
const int YY_HTMLParser_CLASS::BASEFONT=267;
const int YY_HTMLParser_CLASS::BIG=268;
const int YY_HTMLParser_CLASS::BLOCKQUOTE=269;
const int YY_HTMLParser_CLASS::BODY=270;
const int YY_HTMLParser_CLASS::BR=271;
const int YY_HTMLParser_CLASS::CAPTION=272;
const int YY_HTMLParser_CLASS::CENTER=273;
const int YY_HTMLParser_CLASS::CITE=274;
const int YY_HTMLParser_CLASS::CODE=275;
const int YY_HTMLParser_CLASS::DD=276;
const int YY_HTMLParser_CLASS::DFN=277;
const int YY_HTMLParser_CLASS::DIR=278;
const int YY_HTMLParser_CLASS::DIV=279;
const int YY_HTMLParser_CLASS::DL=280;
const int YY_HTMLParser_CLASS::DT=281;
const int YY_HTMLParser_CLASS::EM=282;
const int YY_HTMLParser_CLASS::FONT=283;
const int YY_HTMLParser_CLASS::FORM=284;
const int YY_HTMLParser_CLASS::H1=285;
const int YY_HTMLParser_CLASS::H2=286;
const int YY_HTMLParser_CLASS::H3=287;
const int YY_HTMLParser_CLASS::H4=288;
const int YY_HTMLParser_CLASS::H5=289;
const int YY_HTMLParser_CLASS::H6=290;
const int YY_HTMLParser_CLASS::HEAD=291;
const int YY_HTMLParser_CLASS::HR=292;
const int YY_HTMLParser_CLASS::HTML=293;
const int YY_HTMLParser_CLASS::I=294;
const int YY_HTMLParser_CLASS::IMG=295;
const int YY_HTMLParser_CLASS::INPUT=296;
const int YY_HTMLParser_CLASS::ISINDEX=297;
const int YY_HTMLParser_CLASS::KBD=298;
const int YY_HTMLParser_CLASS::LI=299;
const int YY_HTMLParser_CLASS::LINK=300;
const int YY_HTMLParser_CLASS::MAP=301;
const int YY_HTMLParser_CLASS::MENU=302;
const int YY_HTMLParser_CLASS::META=303;
const int YY_HTMLParser_CLASS::NOBR=304;
const int YY_HTMLParser_CLASS::OL=305;
const int YY_HTMLParser_CLASS::OPTION=306;
const int YY_HTMLParser_CLASS::P=307;
const int YY_HTMLParser_CLASS::PARAM=308;
const int YY_HTMLParser_CLASS::PRE=309;
const int YY_HTMLParser_CLASS::SAMP=310;
const int YY_HTMLParser_CLASS::SCRIPT=311;
const int YY_HTMLParser_CLASS::SELECT=312;
const int YY_HTMLParser_CLASS::SMALL=313;
const int YY_HTMLParser_CLASS::STRIKE=314;
const int YY_HTMLParser_CLASS::STRONG=315;
const int YY_HTMLParser_CLASS::STYLE=316;
const int YY_HTMLParser_CLASS::SUB=317;
const int YY_HTMLParser_CLASS::SUP=318;
const int YY_HTMLParser_CLASS::TABLE=319;
const int YY_HTMLParser_CLASS::TD=320;
const int YY_HTMLParser_CLASS::TEXTAREA=321;
const int YY_HTMLParser_CLASS::TH=322;
const int YY_HTMLParser_CLASS::TITLE=323;
const int YY_HTMLParser_CLASS::TR=324;
const int YY_HTMLParser_CLASS::TT=325;
const int YY_HTMLParser_CLASS::U=326;
const int YY_HTMLParser_CLASS::UL=327;
const int YY_HTMLParser_CLASS::VAR=328;
const int YY_HTMLParser_CLASS::END_A=329;
const int YY_HTMLParser_CLASS::END_ADDRESS=330;
const int YY_HTMLParser_CLASS::END_APPLET=331;
const int YY_HTMLParser_CLASS::END_B=332;
const int YY_HTMLParser_CLASS::END_BIG=333;
const int YY_HTMLParser_CLASS::END_BLOCKQUOTE=334;
const int YY_HTMLParser_CLASS::END_BODY=335;
const int YY_HTMLParser_CLASS::END_CAPTION=336;
const int YY_HTMLParser_CLASS::END_CENTER=337;
const int YY_HTMLParser_CLASS::END_CITE=338;
const int YY_HTMLParser_CLASS::END_CODE=339;
const int YY_HTMLParser_CLASS::END_DD=340;
const int YY_HTMLParser_CLASS::END_DFN=341;
const int YY_HTMLParser_CLASS::END_DIR=342;
const int YY_HTMLParser_CLASS::END_DIV=343;
const int YY_HTMLParser_CLASS::END_DL=344;
const int YY_HTMLParser_CLASS::END_DT=345;
const int YY_HTMLParser_CLASS::END_EM=346;
const int YY_HTMLParser_CLASS::END_FONT=347;
const int YY_HTMLParser_CLASS::END_FORM=348;
const int YY_HTMLParser_CLASS::END_H1=349;
const int YY_HTMLParser_CLASS::END_H2=350;
const int YY_HTMLParser_CLASS::END_H3=351;
const int YY_HTMLParser_CLASS::END_H4=352;
const int YY_HTMLParser_CLASS::END_H5=353;
const int YY_HTMLParser_CLASS::END_H6=354;
const int YY_HTMLParser_CLASS::END_HEAD=355;
const int YY_HTMLParser_CLASS::END_HTML=356;
const int YY_HTMLParser_CLASS::END_I=357;
const int YY_HTMLParser_CLASS::END_KBD=358;
const int YY_HTMLParser_CLASS::END_LI=359;
const int YY_HTMLParser_CLASS::END_MAP=360;
const int YY_HTMLParser_CLASS::END_MENU=361;
const int YY_HTMLParser_CLASS::END_NOBR=362;
const int YY_HTMLParser_CLASS::END_OL=363;
const int YY_HTMLParser_CLASS::END_OPTION=364;
const int YY_HTMLParser_CLASS::END_P=365;
const int YY_HTMLParser_CLASS::END_PRE=366;
const int YY_HTMLParser_CLASS::END_SAMP=367;
const int YY_HTMLParser_CLASS::END_SCRIPT=368;
const int YY_HTMLParser_CLASS::END_SELECT=369;
const int YY_HTMLParser_CLASS::END_SMALL=370;
const int YY_HTMLParser_CLASS::END_STRIKE=371;
const int YY_HTMLParser_CLASS::END_STRONG=372;
const int YY_HTMLParser_CLASS::END_STYLE=373;
const int YY_HTMLParser_CLASS::END_SUB=374;
const int YY_HTMLParser_CLASS::END_SUP=375;
const int YY_HTMLParser_CLASS::END_TABLE=376;
const int YY_HTMLParser_CLASS::END_TD=377;
const int YY_HTMLParser_CLASS::END_TEXTAREA=378;
const int YY_HTMLParser_CLASS::END_TH=379;
const int YY_HTMLParser_CLASS::END_TITLE=380;
const int YY_HTMLParser_CLASS::END_TR=381;
const int YY_HTMLParser_CLASS::END_TT=382;
const int YY_HTMLParser_CLASS::END_U=383;
const int YY_HTMLParser_CLASS::END_UL=384;
const int YY_HTMLParser_CLASS::END_VAR=385;
#line 282 "/usr/local/lib/bison.cc"
/* const YY_HTMLParser_CLASS::token */
/*apres const */
YY_HTMLParser_CLASS::YY_HTMLParser_CLASS(YY_HTMLParser_CONSTRUCTOR_PARAM) YY_HTMLParser_CONSTRUCTOR_INIT
{
#if YY_HTMLParser_DEBUG != 0
YY_HTMLParser_DEBUG_FLAG=0;
#endif
YY_HTMLParser_CONSTRUCTOR_CODE;
};
#endif
/* #line 292 "/usr/local/lib/bison.cc" */
#define YYFINAL 286
#define YYFLAG -32768
#define YYNTBASE 131
#define YYTRANSLATE(x) ((unsigned)(x) <= 385 ? yytranslate[x] : 209)
static const short yytranslate[] = { 0,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 1, 2, 3, 4, 5,
6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
26, 27, 28, 29, 30, 31, 32, 33, 34, 35,
36, 37, 38, 39, 40, 41, 42, 43, 44, 45,
46, 47, 48, 49, 50, 51, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 62, 63, 64, 65,
66, 67, 68, 69, 70, 71, 72, 73, 74, 75,
76, 77, 78, 79, 80, 81, 82, 83, 84, 85,
86, 87, 88, 89, 90, 91, 92, 93, 94, 95,
96, 97, 98, 99, 100, 101, 102, 103, 104, 105,
106, 107, 108, 109, 110, 111, 112, 113, 114, 115,
116, 117, 118, 119, 120, 121, 122, 123, 124, 125,
126, 127, 128, 129, 130
};
#if YY_HTMLParser_DEBUG != 0
static const short yyprhs[] = { 0,
0, 2, 3, 6, 9, 12, 15, 18, 21, 26,
29, 32, 35, 38, 41, 44, 47, 50, 53, 56,
59, 62, 64, 65, 68, 71, 74, 77, 80, 83,
86, 90, 92, 96, 97, 100, 103, 106, 108, 110,
112, 116, 120, 124, 128, 130, 135, 136, 141, 142,
147, 148, 153, 154, 159, 160, 163, 166, 170, 172,
174, 180, 186, 187, 189, 192, 195, 199, 205, 209,
215, 217, 220, 223, 225, 227, 229, 233, 237, 238,
241, 246, 247, 250, 255, 261, 264, 268, 270, 273,
276, 279, 282, 285, 288, 293, 297, 301, 305, 309,
313, 317, 321, 325, 329, 333, 337, 341, 345, 349,
353, 357, 361, 366, 368, 372, 376, 378, 380, 384,
385, 388, 391, 392, 395, 398, 400, 404, 408, 410,
413, 417, 419, 421, 423, 425, 427, 429, 431, 433,
435, 437, 439, 441, 442, 444, 445, 447, 448, 450,
451, 453, 454, 456, 457, 459, 460, 462, 463, 465,
466, 468, 469, 471, 472, 474, 475, 477, 478, 480,
481, 483, 484, 486, 487, 489, 490, 492, 493, 495,
496, 498, 499, 501, 502, 504, 505, 507, 508, 510,
511, 513, 514, 516, 517, 519, 520, 522, 523, 525,
526, 528, 529, 531, 532, 534, 535, 537, 538, 540,
541, 543, 544, 546, 547, 549, 550, 552, 553, 555,
556, 558, 559
};
#endif
static const short yyrhs[] = { 132,
0, 0, 132, 1, 0, 132, 3, 0, 132, 38,
0, 132, 101, 0, 132, 36, 0, 132, 100, 0,
132, 68, 169, 202, 0, 132, 42, 0, 132, 11,
0, 132, 48, 0, 132, 45, 0, 132, 56, 0,
132, 61, 0, 132, 15, 0, 132, 80, 0, 132,
157, 0, 132, 135, 0, 132, 136, 0, 132, 156,
0, 4, 0, 0, 134, 1, 0, 134, 56, 0,
134, 61, 0, 134, 157, 0, 134, 135, 0, 134,
136, 0, 134, 156, 0, 167, 137, 168, 0, 138,
0, 52, 137, 192, 0, 0, 137, 1, 0, 137,
157, 0, 137, 138, 0, 139, 0, 152, 0, 146,
0, 24, 134, 183, 0, 18, 134, 179, 0, 14,
134, 177, 0, 29, 134, 187, 0, 37, 0, 64,
170, 154, 121, 0, 0, 50, 140, 144, 108, 0,
0, 72, 141, 144, 206, 0, 0, 23, 142, 144,
87, 0, 0, 47, 143, 144, 106, 0, 0, 144,
1, 0, 144, 145, 0, 44, 172, 190, 0, 136,
0, 157, 0, 25, 172, 208, 146, 184, 0, 25,
172, 208, 147, 89, 0, 0, 147, 0, 147, 148,
0, 147, 149, 0, 26, 172, 208, 0, 26, 172,
90, 174, 208, 0, 21, 172, 208, 0, 21, 172,
85, 174, 208, 0, 151, 0, 150, 1, 0, 150,
151, 0, 158, 0, 135, 0, 136, 0, 54, 171,
193, 0, 17, 171, 81, 0, 0, 154, 1, 0,
154, 69, 155, 203, 0, 0, 155, 1, 0, 155,
65, 134, 200, 0, 155, 67, 134, 201, 200, 0,
155, 41, 0, 7, 171, 75, 0, 158, 0, 157,
158, 0, 133, 208, 0, 159, 208, 0, 160, 208,
0, 161, 208, 0, 164, 208, 0, 49, 171, 107,
208, 0, 70, 171, 204, 0, 39, 171, 188, 0,
10, 171, 176, 0, 71, 171, 205, 0, 59, 171,
196, 0, 13, 171, 178, 0, 58, 171, 195, 0,
62, 171, 198, 0, 63, 171, 199, 0, 27, 171,
185, 0, 60, 171, 197, 0, 22, 171, 182, 0,
20, 171, 181, 0, 55, 171, 194, 0, 43, 171,
189, 0, 73, 171, 207, 0, 19, 171, 180, 0,
6, 173, 172, 175, 0, 40, 0, 8, 162, 76,
0, 28, 172, 186, 0, 12, 0, 16, 0, 46,
163, 105, 0, 0, 162, 158, 0, 162, 53, 0,
0, 163, 1, 0, 163, 9, 0, 41, 0, 57,
165, 114, 0, 66, 133, 123, 0, 166, 0, 165,
166, 0, 51, 133, 191, 0, 30, 0, 31, 0,
32, 0, 33, 0, 34, 0, 35, 0, 94, 0,
95, 0, 96, 0, 97, 0, 98, 0, 99, 0,
0, 133, 0, 0, 153, 0, 0, 157, 0, 0,
150, 0, 0, 44, 0, 0, 52, 0, 0, 74,
0, 0, 77, 0, 0, 79, 0, 0, 78, 0,
0, 82, 0, 0, 83, 0, 0, 84, 0, 0,
86, 0, 0, 88, 0, 0, 89, 0, 0, 91,
0, 0, 92, 0, 0, 93, 0, 0, 102, 0,
0, 103, 0, 0, 104, 0, 0, 109, 0, 0,
110, 0, 0, 111, 0, 0, 112, 0, 0, 115,
0, 0, 116, 0, 0, 117, 0, 0, 119, 0,
0, 120, 0, 0, 122, 0, 0, 124, 0, 0,
125, 0, 0, 126, 0, 0, 127, 0, 0, 128,
0, 0, 129, 0, 0, 130, 0, 0, 1, 0
};
#if YY_HTMLParser_DEBUG != 0
static const short yyrline[] = { 0,
273, 304, 309, 312, 315, 319, 322, 326, 329, 333,
336, 339, 342, 345, 353, 361, 365, 368, 373, 376,
379, 384, 392, 396, 399, 407, 415, 420, 423, 426,
431, 442, 446, 454, 458, 461, 466, 471, 475, 478,
481, 487, 493, 499, 505, 510, 519, 520, 527, 527,
534, 534, 541, 541, 550, 554, 557, 563, 570, 575,
582, 591, 600, 604, 607, 611, 617, 623, 631, 637,
645, 650, 653, 658, 662, 665, 670, 678, 686, 690,
693, 701, 705, 708, 714, 721, 727, 737, 742, 747,
749, 750, 751, 752, 753, 761, 763, 764, 765, 766,
767, 768, 769, 770, 773, 775, 776, 777, 778, 779,
780, 781, 784, 795, 800, 808, 814, 819, 824, 832,
836, 840, 848, 852, 855, 861, 867, 873, 881, 886,
891, 901, 903, 904, 905, 906, 907, 910, 912, 913,
914, 915, 916, 921, 921, 922, 922, 923, 923, 924,
924, 926, 926, 927, 927, 929, 929, 930, 930, 931,
931, 932, 932, 933, 933, 934, 934, 935, 935, 936,
936, 937, 937, 938, 938, 939, 939, 940, 940, 941,
941, 942, 942, 943, 943, 944, 944, 945, 945, 946,
946, 947, 947, 948, 948, 949, 949, 950, 950, 951,
951, 952, 952, 953, 953, 954, 954, 955, 955, 956,
956, 957, 957, 958, 958, 959, 959, 960, 960, 961,
961, 963, 963
};
static const char * const yytname[] = { "$","error","$illegal.","DOCTYPE",
"PCDATA","SCAN_ERROR","A","ADDRESS","APPLET","AREA","B","BASE","BASEFONT","BIG",
"BLOCKQUOTE","BODY","BR","CAPTION","CENTER","CITE","CODE","DD","DFN","DIR","DIV",
"DL","DT","EM","FONT","FORM","H1","H2","H3","H4","H5","H6","HEAD","HR","HTML",
"I","IMG","INPUT","ISINDEX","KBD","LI","LINK","MAP","MENU","META","NOBR","OL",
"OPTION","P","PARAM","PRE","SAMP","SCRIPT","SELECT","SMALL","STRIKE","STRONG",
"STYLE","SUB","SUP","TABLE","TD","TEXTAREA","TH","TITLE","TR","TT","U","UL",
"VAR","END_A","END_ADDRESS","END_APPLET","END_B","END_BIG","END_BLOCKQUOTE",
"END_BODY","END_CAPTION","END_CENTER","END_CITE","END_CODE","END_DD","END_DFN",
"END_DIR","END_DIV","END_DL","END_DT","END_EM","END_FONT","END_FORM","END_H1",
"END_H2","END_H3","END_H4","END_H5","END_H6","END_HEAD","END_HTML","END_I","END_KBD",
"END_LI","END_MAP","END_MENU","END_NOBR","END_OL","END_OPTION","END_P","END_PRE",
"END_SAMP","END_SCRIPT","END_SELECT","END_SMALL","END_STRIKE","END_STRONG","END_STYLE",
"END_SUB","END_SUP","END_TABLE","END_TD","END_TEXTAREA","END_TH","END_TITLE",
"END_TR","END_TT","END_U","END_UL","END_VAR","document","document_","pcdata",
"body_content","heading","block","paragraph_content","block_except_p","list",
"@1","@2","@3","@4","list_content","list_item","definition_list","definition_list_content",
"term_name","term_definition","flow","flow_","preformatted","caption","table_rows",
"table_cells","address","texts","text","font","phrase","special","applet_content",
"map_content","form","select_content","option","HX","END_HX","opt_pcdata","opt_caption",
"opt_texts","opt_flow","opt_LI","opt_P","opt_END_A","opt_END_B","opt_END_BLOCKQUOTE",
"opt_END_BIG","opt_END_CENTER","opt_END_CITE","opt_END_CODE","opt_END_DFN","opt_END_DIV",
"opt_END_DL","opt_END_EM","opt_END_FONT","opt_END_FORM","opt_END_I","opt_END_KBD",
"opt_END_LI","opt_END_OPTION","opt_END_P","opt_END_PRE","opt_END_SAMP","opt_END_SMALL",
"opt_END_STRIKE","opt_END_STRONG","opt_END_SUB","opt_END_SUP","opt_END_TD","opt_END_TH",
"opt_END_TITLE","opt_END_TR","opt_END_TT","opt_END_U","opt_END_UL","opt_END_VAR",
"opt_error",""
};
#endif
static const short yyr1[] = { 0,
131, 132, 132, 132, 132, 132, 132, 132, 132, 132,
132, 132, 132, 132, 132, 132, 132, 132, 132, 132,
132, 133, 134, 134, 134, 134, 134, 134, 134, 134,
135, 136, 136, 137, 137, 137, 137, 138, 138, 138,
138, 138, 138, 138, 138, 138, 140, 139, 141, 139,
142, 139, 143, 139, 144, 144, 144, 145, 145, 145,
146, 146, 147, 147, 147, 147, 148, 148, 149, 149,
150, 150, 150, 151, 151, 151, 152, 153, 154, 154,
154, 155, 155, 155, 155, 155, 156, 157, 157, 158,
158, 158, 158, 158, 158, 159, 159, 159, 159, 159,
159, 159, 159, 159, 160, 160, 160, 160, 160, 160,
160, 160, 161, 161, 161, 161, 161, 161, 161, 162,
162, 162, 163, 163, 163, 164, 164, 164, 165, 165,
166, 167, 167, 167, 167, 167, 167, 168, 168, 168,
168, 168, 168, 169, 169, 170, 170, 171, 171, 172,
172, 173, 173, 174, 174, 175, 175, 176, 176, 177,
177, 178, 178, 179, 179, 180, 180, 181, 181, 182,
182, 183, 183, 184, 184, 185, 185, 186, 186, 187,
187, 188, 188, 189, 189, 190, 190, 191, 191, 192,
192, 193, 193, 194, 194, 195, 195, 196, 196, 197,
197, 198, 198, 199, 199, 200, 200, 201, 201, 202,
202, 203, 203, 204, 204, 205, 205, 206, 206, 207,
207, 208, 208
};
static const short yyr2[] = { 0,
1, 0, 2, 2, 2, 2, 2, 2, 4, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 1, 0, 2, 2, 2, 2, 2, 2, 2,
3, 1, 3, 0, 2, 2, 2, 1, 1, 1,
3, 3, 3, 3, 1, 4, 0, 4, 0, 4,
0, 4, 0, 4, 0, 2, 2, 3, 1, 1,
5, 5, 0, 1, 2, 2, 3, 5, 3, 5,
1, 2, 2, 1, 1, 1, 3, 3, 0, 2,
4, 0, 2, 4, 5, 2, 3, 1, 2, 2,
2, 2, 2, 2, 4, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 4, 1, 3, 3, 1, 1, 3, 0,
2, 2, 0, 2, 2, 1, 3, 3, 1, 2,
3, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 1
};
static const short yydefact[] = { 2,
0, 3, 4, 22, 152, 148, 120, 148, 11, 117,
148, 23, 16, 118, 23, 148, 148, 148, 51, 23,
150, 148, 150, 23, 132, 133, 134, 135, 136, 137,
7, 45, 5, 148, 114, 126, 10, 148, 13, 123,
53, 12, 148, 47, 34, 148, 148, 14, 0, 148,
148, 148, 15, 148, 148, 146, 0, 144, 148, 148,
49, 148, 17, 8, 6, 0, 19, 20, 32, 38,
40, 39, 21, 18, 88, 0, 0, 0, 0, 34,
153, 150, 149, 0, 0, 158, 162, 0, 0, 166,
168, 170, 55, 0, 75, 76, 0, 71, 74, 0,
176, 178, 0, 182, 184, 0, 55, 0, 55, 0,
192, 194, 0, 0, 129, 196, 198, 200, 202, 204,
148, 147, 79, 0, 145, 210, 214, 216, 55, 220,
223, 90, 89, 91, 92, 93, 94, 0, 156, 87,
122, 115, 121, 159, 98, 163, 101, 24, 25, 26,
161, 28, 29, 30, 27, 43, 165, 42, 167, 112,
169, 108, 171, 107, 0, 173, 41, 72, 73, 63,
177, 105, 179, 116, 181, 44, 183, 97, 185, 110,
124, 125, 119, 0, 0, 0, 35, 191, 37, 36,
33, 193, 77, 195, 109, 188, 127, 130, 197, 102,
199, 100, 201, 106, 203, 103, 205, 104, 0, 0,
128, 211, 9, 215, 96, 217, 99, 0, 221, 111,
138, 139, 140, 141, 142, 143, 31, 157, 113, 56,
150, 52, 59, 57, 60, 174, 0, 54, 95, 48,
189, 131, 78, 80, 82, 46, 219, 50, 186, 175,
61, 150, 150, 62, 65, 66, 0, 187, 58, 0,
0, 83, 86, 23, 23, 213, 81, 154, 69, 154,
67, 0, 0, 155, 0, 0, 207, 84, 209, 206,
70, 68, 85, 0, 0, 0
};
static const short yydefgoto[] = { 284,
1, 66, 88, 95, 96, 110, 69, 70, 109, 129,
93, 107, 165, 234, 71, 237, 255, 256, 97, 98,
72, 122, 210, 257, 154, 83, 75, 76, 77, 78,
85, 106, 79, 114, 115, 80, 227, 126, 123, 84,
100, 82, 275, 229, 145, 156, 147, 158, 160, 162,
164, 167, 251, 172, 174, 176, 178, 180, 259, 242,
191, 193, 195, 200, 202, 204, 206, 208, 278, 280,
213, 267, 215, 217, 248, 220, 132
};
static const short yypact[] = {-32768,
1740,-32768,-32768,-32768, -24, 2148,-32768, 2148,-32768,-32768,
2148,-32768,-32768,-32768,-32768, 2148, 2148, 2148,-32768,-32768,
2078, 2148, 2078,-32768,-32768,-32768,-32768,-32768,-32768,-32768,
-32768,-32768,-32768, 2148,-32768,-32768,-32768, 2148,-32768,-32768,
-32768,-32768, 2148,-32768,-32768, 2148, 2148,-32768, -26, 2148,
2148, 2148,-32768, 2148, 2148, 14, 28, 28, 2148, 2148,
-32768, 2148,-32768,-32768,-32768, 283,-32768,-32768,-32768,-32768,
-32768,-32768,-32768, 2148,-32768, 283, 283, 283, 283,-32768,
-32768, 2078, 2148, -42, 2007, -43, -41, 414, 545, -48,
-45, -46,-32768, 676,-32768,-32768, 807,-32768,-32768, 21,
-50, -40, 938, -58, -52, 8,-32768, -51,-32768, 1069,
-53, -49, 28, -32,-32768, -56, -55, -47, -57, -39,
2148,-32768,-32768, -59,-32768, -36, -60, -54,-32768, -44,
-32768,-32768,-32768,-32768,-32768,-32768,-32768, 1838, -2,-32768,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,
-32768,-32768,-32768,-32768, 2148,-32768,-32768,-32768,-32768,-32768,
-32768,-32768,-32768,-32768, 1937,-32768,-32768,-32768,-32768, 50,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,
-32768,-32768,-32768, 1660, 283, 1587,-32768,-32768,-32768, 2148,
-32768,-32768,-32768,-32768,-32768, -31,-32768,-32768,-32768,-32768,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768, -4, 7,
-32768,-32768,-32768,-32768,-32768,-32768,-32768, 1200,-32768,-32768,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,
2078,-32768,-32768,-32768, 2148, -6, -5,-32768,-32768,-32768,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768, -19,-32768,
-32768, 2078, 2078,-32768,-32768,-32768, 4,-32768,-32768, 29,
17,-32768,-32768,-32768,-32768,-32768,-32768, 40,-32768, 40,
-32768, 1454, 1330,-32768, 27, 27,-32768,-32768,-32768, -28,
-32768,-32768,-32768, 95, 99,-32768
};
static const short yypgoto[] = {-32768,
-32768, -34, -13, 9, 2, 20, -84,-32768,-32768,-32768,
-32768,-32768, -80,-32768, -69,-32768,-32768,-32768,-32768, 11,
-32768,-32768,-32768,-32768, 103, -1, -17,-32768,-32768,-32768,
-32768,-32768,-32768,-32768, -3,-32768,-32768,-32768,-32768, 1527,
-22,-32768, -155,-32768,-32768,-32768,-32768,-32768,-32768,-32768,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768,
-32768,-32768,-32768,-32768,-32768,-32768,-32768,-32768, -163,-32768,
-32768,-32768,-32768,-32768,-32768,-32768, -64
};
#define YYLAST 2221
static const short yytable[] = { 74,
102, 89, 68, 99, 262, 99, 94, 244, 181, 67,
103, 134, 135, 136, 137, 252, 182, 131, 113, 81,
253, 131, 124, 125, 113, 189, 184, 131, 186, 131,
121, 4, 140, 144, 159, 170, 146, -222, 161, 163,
171, -222, -222, 177, 263, -222, -222, -222, 218, -222,
179, 173, -222, 189, -222, 185, 133, 192, 199, 139,
201, 205, 194, 211, 99, 133, 214, 143, 264, 203,
265, 228, -212, 216, 21, 245, 243, 241, 196, 99,
207, 197, 250, 254, 258, 219, 155, 155, 212, 153,
153, 274, 155, 277, 285, 153, 152, 152, 286, 138,
236, 155, 152, 73, 153, -222, 270, 169, 190, -222,
198, 152, 183, 268, 276, -222, 283, -222, 0, 0,
239, 0, 0, 0, -212, 0, 0, 246, 0, 266,
0, 0, 0, 0, 0, 0, 190, 133, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 235, 0, 0, 233, 0, 0, 0,
0, 0, 133, 0, 0, 0, 0, 0, 0, 0,
0, 0, 235, 0, 235, 233, 0, 233, 0, 0,
0, 0, 0, 0, 0, 269, 271, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 249, 0,
281, 282, 0, 99, 0, 0, 235, 133, 0, 233,
0, 0, 0, 0, 0, 0, 0, 0, 0, 260,
261, 0, 0, 0, 99, 99, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
272, 273, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
155, 155, 0, 153, 153, 0, 0, 0, 0, 0,
152, 152, -222, 131, 0, -222, -222, 0, -222, -222,
-222, 0, -222, -222, -222, -222, -222, -222, -222, 0,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, 0, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, -222, -222, -222,
-222, -222, -222, -222, -222, -222, -222, 0, -222, -222,
-222, 0, -222, -222, -222, 0, 0, -222, -222, -222,
0, -222, -222, -222, -222, 0, -222, 0, -222, -222,
-222, -222, -222, -160, 148, 0, -160, 4, 0, 5,
6, 7, 0, 8, -160, 10, 11, 12, -160, 14,
0, 15, 16, 17, -160, 18, 19, 20, 21, -160,
22, 23, 24, 25, 26, 27, 28, 29, 30, -160,
32, -160, 34, 35, 36, -160, 38, -160, -160, 40,
41, -160, 43, 44, 0, 45, -160, 46, 47, 149,
49, 50, 51, 52, 150, 54, 55, 56, -160, 57,
-160, -160, -160, 59, 60, 61, 62, -160, -160, -160,
-160, -160, 151, -160, -160, -160, -160, -160, -160, -160,
-160, -160, -160, -160, -160, -160, -160, -160, -160, -160,
-160, -160, -160, -160, -160, -160, -160, -160, 0, -160,
-160, -160, 0, -160, -160, -160, 0, 0, -160, -160,
-160, 0, -160, -160, -160, -160, 0, -160, 0, -160,
-160, -160, -160, -160, -164, 148, 0, -164, 4, 0,
5, 6, 7, 0, 8, -164, 10, 11, 12, -164,
14, 0, 15, 16, 17, -164, 18, 19, 20, 21,
-164, 22, 23, 24, 25, 26, 27, 28, 29, 30,
-164, 32, -164, 34, 35, 36, -164, 38, -164, -164,
40, 41, -164, 43, 44, 0, 45, -164, 46, 47,
149, 49, 50, 51, 52, 150, 54, 55, 56, -164,
57, -164, -164, -164, 59, 60, 61, 62, -164, -164,
-164, -164, -164, -164, -164, -164, 157, -164, -164, -164,
-164, -164, -164, -164, -164, -164, -164, -164, -164, -164,
-164, -164, -164, -164, -164, -164, -164, -164, -164, 0,
-164, -164, -164, 0, -164, -164, -164, 0, 0, -164,
-164, -164, 0, -164, -164, -164, -164, 0, -164, 0,
-164, -164, -164, -164, -164, -172, 148, 0, -172, 4,
0, 5, 6, 7, 0, 8, -172, 10, 11, 12,
-172, 14, 0, 15, 16, 17, -172, 18, 19, 20,
21, -172, 22, 23, 24, 25, 26, 27, 28, 29,
30, -172, 32, -172, 34, 35, 36, -172, 38, -172,
-172, 40, 41, -172, 43, 44, 0, 45, -172, 46,
47, 149, 49, 50, 51, 52, 150, 54, 55, 56,
-172, 57, -172, -172, -172, 59, 60, 61, 62, -172,
-172, -172, -172, -172, -172, -172, -172, -172, -172, -172,
-172, -172, -172, 166, -172, -172, -172, -172, -172, -172,
-172, -172, -172, -172, -172, -172, -172, -172, -172, -172,
0, -172, -172, -172, 0, -172, -172, -172, 0, 0,
-172, -172, -172, 0, -172, -172, -172, -172, 0, -172,
0, -172, -172, -172, -172, -172, -151, 168, 0, -151,
4, 0, 5, -151, 7, 0, 8, -151, 10, 11,
12, -151, 14, 0, 15, 16, 17, -151, 18, 19,
20, 21, -151, 22, 23, 24, 25, 26, 27, 28,
29, 30, -151, 32, -151, 34, 35, 36, -151, 38,
-151, -151, 40, 41, -151, 43, 44, 0, 45, -151,
46, 47, -151, 49, 50, 51, 52, -151, 54, 55,
56, -151, 57, -151, -151, -151, 59, 60, 61, 62,
-151, -151, -151, -151, -151, -151, -151, -151, -151, -151,
-151, -151, -151, -151, -151, -151, -151, -151, -151, -151,
-151, -151, -151, -151, -151, -151, -151, -151, -151, -151,
-151, 0, -151, -151, -151, 0, -151, -151, -151, 0,
0, -151, -151, -151, 0, -151, -151, -151, -151, 0,
-151, 0, -151, -151, -151, -151, -151, -180, 148, 0,
-180, 4, 0, 5, 6, 7, 0, 8, -180, 10,
11, 12, -180, 14, 0, 15, 16, 17, -180, 18,
19, 20, 21, -180, 22, 23, 24, 25, 26, 27,
28, 29, 30, -180, 32, -180, 34, 35, 36, -180,
38, -180, -180, 40, 41, -180, 43, 44, 0, 45,
-180, 46, 47, 149, 49, 50, 51, 52, 150, 54,
55, 56, -180, 57, -180, -180, -180, 59, 60, 61,
62, -180, -180, -180, -180, -180, -180, -180, -180, -180,
-180, -180, -180, -180, -180, -180, -180, -180, -180, -180,
175, -180, -180, -180, -180, -180, -180, -180, -180, -180,
-180, -180, 0, -180, -180, -180, 0, -180, -180, -180,
0, 0, -180, -180, -180, 0, -180, -180, -180, -180,
0, -180, 0, -180, -180, -180, -180, -180, -190, 187,
0, -190, 4, 0, 5, -190, 7, 0, 8, -190,
10, 11, 12, -190, 14, 0, 15, 16, 17, -190,
18, 19, 20, 21, -190, 22, 23, 24, -190, -190,
-190, -190, -190, -190, -190, 32, -190, 34, 35, 36,
-190, 38, -190, -190, 40, 41, -190, 43, 44, 0,
-190, -190, 46, 47, -190, 49, 50, 51, 52, -190,
54, 55, 56, -190, 57, -190, -190, -190, 59, 60,
61, 62, -190, -190, -190, -190, -190, -190, -190, -190,
-190, -190, -190, -190, -190, -190, -190, -190, -190, -190,
-190, -190, -190, -190, -190, -190, -190, -190, -190, -190,
-190, -190, -190, 0, -190, -190, -190, 0, 188, -190,
-190, 0, 0, -190, -190, -190, 0, -190, -190, -190,
-190, 0, -190, 0, -190, -190, -190, -190, -190, -218,
230, 0, -218, 4, 0, 5, -218, 7, 0, 8,
-218, 10, 11, 12, -218, 14, 0, 15, 16, 17,
-218, 18, 19, 20, 21, -218, 22, 23, 24, -218,
-218, -218, -218, -218, -218, -218, 32, -218, 34, 35,
36, -218, 38, 231, -218, 40, 41, -218, 43, 44,
0, 45, -218, 46, 47, -218, 49, 50, 51, 52,
-218, 54, 55, 56, -218, 57, -218, -218, -218, 59,
60, 61, 62, -218, -218, -218, -218, -218, -218, -218,
-218, -218, -218, -218, -218, -218, -218, -218, -218, -218,
-218, -218, -218, -218, -218, -218, -218, -218, -218, -218,
-218, -218, -218, -218, 0, -218, -218, -218, 0, -218,
-218, -218, 0, 0, -218, -218, -218, 0, -218, -218,
-218, -218, 0, -218, 0, -218, -218, -218, 247, -218,
148, 0, 0, 4, 0, 5, 6, 7, 0, 8,
0, 10, 11, 12, 0, 14, 0, 15, 16, 17,
0, 18, 19, 20, 21, 0, 22, 23, 24, 25,
26, 27, 28, 29, 30, 0, 32, 0, 34, 35,
36, 0, 38, 0, 0, 40, 41, 0, 43, 44,
0, 45, 0, 46, 47, 149, 49, 50, 51, 52,
150, 54, 55, 56, -208, 57, -208, 0, -208, 59,
60, 61, 62, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-208, -208, 0, 279, 148, -208, 0, 4, 0, 5,
6, 7, 0, 8, 0, 10, 11, 12, 0, 14,
0, 15, 16, 17, 0, 18, 19, 20, 21, 0,
22, 23, 24, 25, 26, 27, 28, 29, 30, 0,
32, 0, 34, 35, 36, 0, 38, 0, 0, 40,
41, 0, 43, 44, 0, 45, 0, 46, 47, 149,
49, 50, 51, 52, 150, 54, 55, 56, -206, 57,
-206, 0, -206, 59, 60, 61, 62, 0, 0, 0,
0, 0, 0, 0, 86, 0, 0, 87, 0, 0,
0, 0, 90, 91, 92, 0, 0, 0, 101, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
104, 0, 0, 0, 105, 0, 0, 0, 0, 108,
0, 0, 111, 112, -206, 277, 116, 117, 118, -206,
119, 120, 0, 0, 0, 127, 128, 230, 130, 0,
4, 0, 5, 0, 7, 0, 8, 0, 10, 11,
12, 0, 14, 0, 15, 16, 17, 0, 18, 19,
20, 21, 0, 22, 23, 24, 0, 0, 0, 0,
0, 0, 0, 32, 0, 34, 35, 36, 0, 38,
231, 0, 40, 41, 0, 43, 44, 0, 45, 0,
46, 47, 0, 49, 50, 51, 52, 209, 54, 55,
56, 0, 57, 0, 0, 0, 59, 60, 61, 62,
230, 0, 0, 4, 0, 5, 0, 7, 0, 8,
0, 10, 11, 12, 0, 14, 0, 15, 16, 17,
0, 18, 19, 20, 21, 0, 22, 23, 24, 0,
0, 0, 0, 0, 240, 0, 32, 0, 34, 35,
36, 0, 38, 231, 0, 40, 41, 0, 43, 44,
0, 45, 0, 46, 47, 0, 49, 50, 51, 52,
0, 54, 55, 56, 0, 57, 0, 0, 0, 59,
60, 61, 62, 0, 0, 0, 0, 0, 0, -1,
2, 0, 3, 4, 0, 5, 6, 7, 0, 8,
9, 10, 11, 12, 13, 14, 0, 15, 16, 17,
0, 18, 19, 20, 21, 238, 22, 23, 24, 25,
26, 27, 28, 29, 30, 31, 32, 33, 34, 35,
36, 37, 38, 0, 39, 40, 41, 42, 43, 44,
0, 45, 0, 46, 47, 48, 49, 50, 51, 52,
53, 54, 55, 56, 0, 57, 0, 58, 0, 59,
60, 61, 62, 0, 0, 0, 0, 0, 0, 63,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 187, 64,
65, 4, 0, 5, 0, 7, 0, 8, 0, 10,
11, 12, 0, 14, 0, 15, 16, 17, 0, 18,
19, 20, 21, 0, 22, 23, 24, 0, 0, 0,
0, 0, 0, 0, 32, 0, 34, 35, 36, 0,
38, 0, 0, 40, 41, 0, 43, 44, 0, 0,
0, 46, 47, 0, 49, 50, 51, 52, 0, 54,
55, 56, 0, 57, 0, 0, 0, 59, 60, 61,
62, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 221, 222, 223, 224, 225, 226, 230, 0, 0,
4, 0, 5, 0, 7, 0, 8, 0, 10, 11,
12, 0, 14, 0, 15, 16, 17, 0, 18, 19,
20, 21, 0, 22, 23, 24, 0, 0, 0, 0,
0, 0, 0, 32, 0, 34, 35, 36, 0, 38,
231, 0, 40, 41, 0, 43, 44, 0, 45, 0,
46, 47, 0, 49, 50, 51, 52, 0, 54, 55,
56, 0, 57, 0, 0, 0, 59, 60, 61, 62,
4, 0, 5, 0, 7, 0, 8, 0, 10, 11,
0, 0, 14, 232, 0, 16, 17, 0, 18, 0,
0, 0, 0, 22, 23, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 34, 35, 36, 0, 38,
0, 0, 40, 0, 0, 43, 0, 0, 0, 141,
0, 47, 0, 49, 50, 51, 52, 0, 54, 55,
0, 0, 57, 0, 0, 0, 59, 60, 0, 62,
0, 4, 142, 5, 0, 7, 0, 8, 0, 10,
11, 12, 0, 14, 0, 15, 16, 17, 0, 18,
19, 20, 21, 0, 22, 23, 24, 25, 26, 27,
28, 29, 30, 0, 32, 0, 34, 35, 36, 0,
38, 0, 0, 40, 41, 0, 43, 44, 0, 45,
0, 46, 47, 0, 49, 50, 51, 52, 0, 54,
55, 56, 0, 57, 0, 0, 0, 59, 60, 61,
62, 4, 0, 5, 0, 7, 0, 8, 0, 10,
11, 0, 0, 14, 0, 0, 16, 17, 0, 18,
0, 0, 0, 0, 22, 23, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 34, 35, 36, 0,
38, 0, 0, 40, 0, 0, 43, 0, 0, 0,
0, 0, 47, 0, 49, 50, 51, 52, 0, 54,
55, 0, 0, 57, 0, 0, 0, 59, 60, 0,
62
};
static const short yycheck[] = { 1,
23, 15, 1, 21, 1, 23, 20, 1, 1, 1,
24, 76, 77, 78, 79, 21, 9, 1, 51, 44,
26, 1, 57, 58, 51, 110, 107, 1, 109, 1,
17, 4, 75, 77, 83, 100, 78, 21, 84, 86,
91, 21, 26, 102, 41, 25, 26, 21, 129, 21,
103, 92, 26, 138, 26, 107, 74, 111, 115, 82,
116, 119, 112, 123, 82, 83, 127, 85, 65, 117,
67, 74, 69, 128, 25, 69, 81, 109, 113, 97,
120, 114, 89, 89, 104, 130, 88, 89, 125, 88,
89, 52, 94, 122, 0, 94, 88, 89, 0, 80,
170, 103, 94, 1, 103, 89, 90, 97, 110, 89,
114, 103, 105, 85, 270, 89, 280, 89, -1, -1,
185, -1, -1, -1, 121, -1, -1, 121, -1, 126,
-1, -1, -1, -1, -1, -1, 138, 155, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, 165, -1, -1, 165, -1, -1, -1,
-1, -1, 190, -1, -1, -1, -1, -1, -1, -1,
-1, -1, 184, -1, 186, 184, -1, 186, -1, -1,
-1, -1, -1, -1, -1, 260, 261, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, 231, -1,
275, 276, -1, 231, -1, -1, 218, 235, -1, 218,
-1, -1, -1, -1, -1, -1, -1, -1, -1, 252,
253, -1, -1, -1, 252, 253, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
264, 265, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
272, 273, -1, 272, 273, -1, -1, -1, -1, -1,
272, 273, 0, 1, -1, 3, 4, -1, 6, 7,
8, -1, 10, 11, 12, 13, 14, 15, 16, -1,
18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37,
38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
48, 49, 50, -1, 52, 53, 54, 55, 56, 57,
58, 59, 60, 61, 62, 63, 64, 65, 66, 67,
68, 69, 70, 71, 72, 73, 74, 75, 76, 77,
78, 79, 80, 81, 82, 83, 84, 85, 86, 87,
88, 89, 90, 91, 92, 93, 94, 95, 96, 97,
98, 99, 100, 101, 102, 103, 104, -1, 106, 107,
108, -1, 110, 111, 112, -1, -1, 115, 116, 117,
-1, 119, 120, 121, 122, -1, 124, -1, 126, 127,
128, 129, 130, 0, 1, -1, 3, 4, -1, 6,
7, 8, -1, 10, 11, 12, 13, 14, 15, 16,
-1, 18, 19, 20, 21, 22, 23, 24, 25, 26,
27, 28, 29, 30, 31, 32, 33, 34, 35, 36,
37, 38, 39, 40, 41, 42, 43, 44, 45, 46,
47, 48, 49, 50, -1, 52, 53, 54, 55, 56,
57, 58, 59, 60, 61, 62, 63, 64, 65, 66,
67, 68, 69, 70, 71, 72, 73, 74, 75, 76,
77, 78, 79, 80, 81, 82, 83, 84, 85, 86,
87, 88, 89, 90, 91, 92, 93, 94, 95, 96,
97, 98, 99, 100, 101, 102, 103, 104, -1, 106,
107, 108, -1, 110, 111, 112, -1, -1, 115, 116,
117, -1, 119, 120, 121, 122, -1, 124, -1, 126,
127, 128, 129, 130, 0, 1, -1, 3, 4, -1,
6, 7, 8, -1, 10, 11, 12, 13, 14, 15,
16, -1, 18, 19, 20, 21, 22, 23, 24, 25,
26, 27, 28, 29, 30, 31, 32, 33, 34, 35,
36, 37, 38, 39, 40, 41, 42, 43, 44, 45,
46, 47, 48, 49, 50, -1, 52, 53, 54, 55,
56, 57, 58, 59, 60, 61, 62, 63, 64, 65,
66, 67, 68, 69, 70, 71, 72, 73, 74, 75,
76, 77, 78, 79, 80, 81, 82, 83, 84, 85,
86, 87, 88, 89, 90, 91, 92, 93, 94, 95,
96, 97, 98, 99, 100, 101, 102, 103, 104, -1,
106, 107, 108, -1, 110, 111, 112, -1, -1, 115,
116, 117, -1, 119, 120, 121, 122, -1, 124, -1,
126, 127, 128, 129, 130, 0, 1, -1, 3, 4,
-1, 6, 7, 8, -1, 10, 11, 12, 13, 14,
15, 16, -1, 18, 19, 20, 21, 22, 23, 24,
25, 26, 27, 28, 29, 30, 31, 32, 33, 34,
35, 36, 37, 38, 39, 40, 41, 42, 43, 44,
45, 46, 47, 48, 49, 50, -1, 52, 53, 54,
55, 56, 57, 58, 59, 60, 61, 62, 63, 64,
65, 66, 67, 68, 69, 70, 71, 72, 73, 74,
75, 76, 77, 78, 79, 80, 81, 82, 83, 84,
85, 86, 87, 88, 89, 90, 91, 92, 93, 94,
95, 96, 97, 98, 99, 100, 101, 102, 103, 104,
-1, 106, 107, 108, -1, 110, 111, 112, -1, -1,
115, 116, 117, -1, 119, 120, 121, 122, -1, 124,
-1, 126, 127, 128, 129, 130, 0, 1, -1, 3,
4, -1, 6, 7, 8, -1, 10, 11, 12, 13,
14, 15, 16, -1, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50, -1, 52, 53,
54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
64, 65, 66, 67, 68, 69, 70, 71, 72, 73,
74, 75, 76, 77, 78, 79, 80, 81, 82, 83,
84, 85, 86, 87, 88, 89, 90, 91, 92, 93,
94, 95, 96, 97, 98, 99, 100, 101, 102, 103,
104, -1, 106, 107, 108, -1, 110, 111, 112, -1,
-1, 115, 116, 117, -1, 119, 120, 121, 122, -1,
124, -1, 126, 127, 128, 129, 130, 0, 1, -1,
3, 4, -1, 6, 7, 8, -1, 10, 11, 12,
13, 14, 15, 16, -1, 18, 19, 20, 21, 22,
23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
33, 34, 35, 36, 37, 38, 39, 40, 41, 42,
43, 44, 45, 46, 47, 48, 49, 50, -1, 52,
53, 54, 55, 56, 57, 58, 59, 60, 61, 62,
63, 64, 65, 66, 67, 68, 69, 70, 71, 72,
73, 74, 75, 76, 77, 78, 79, 80, 81, 82,
83, 84, 85, 86, 87, 88, 89, 90, 91, 92,
93, 94, 95, 96, 97, 98, 99, 100, 101, 102,
103, 104, -1, 106, 107, 108, -1, 110, 111, 112,
-1, -1, 115, 116, 117, -1, 119, 120, 121, 122,
-1, 124, -1, 126, 127, 128, 129, 130, 0, 1,
-1, 3, 4, -1, 6, 7, 8, -1, 10, 11,
12, 13, 14, 15, 16, -1, 18, 19, 20, 21,
22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
32, 33, 34, 35, 36, 37, 38, 39, 40, 41,
42, 43, 44, 45, 46, 47, 48, 49, 50, -1,
52, 53, 54, 55, 56, 57, 58, 59, 60, 61,
62, 63, 64, 65, 66, 67, 68, 69, 70, 71,
72, 73, 74, 75, 76, 77, 78, 79, 80, 81,
82, 83, 84, 85, 86, 87, 88, 89, 90, 91,
92, 93, 94, 95, 96, 97, 98, 99, 100, 101,
102, 103, 104, -1, 106, 107, 108, -1, 110, 111,
112, -1, -1, 115, 116, 117, -1, 119, 120, 121,
122, -1, 124, -1, 126, 127, 128, 129, 130, 0,
1, -1, 3, 4, -1, 6, 7, 8, -1, 10,
11, 12, 13, 14, 15, 16, -1, 18, 19, 20,
21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
31, 32, 33, 34, 35, 36, 37, 38, 39, 40,
41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
-1, 52, 53, 54, 55, 56, 57, 58, 59, 60,
61, 62, 63, 64, 65, 66, 67, 68, 69, 70,
71, 72, 73, 74, 75, 76, 77, 78, 79, 80,
81, 82, 83, 84, 85, 86, 87, 88, 89, 90,
91, 92, 93, 94, 95, 96, 97, 98, 99, 100,
101, 102, 103, 104, -1, 106, 107, 108, -1, 110,
111, 112, -1, -1, 115, 116, 117, -1, 119, 120,
121, 122, -1, 124, -1, 126, 127, 128, 129, 130,
1, -1, -1, 4, -1, 6, 7, 8, -1, 10,
-1, 12, 13, 14, -1, 16, -1, 18, 19, 20,
-1, 22, 23, 24, 25, -1, 27, 28, 29, 30,
31, 32, 33, 34, 35, -1, 37, -1, 39, 40,
41, -1, 43, -1, -1, 46, 47, -1, 49, 50,
-1, 52, -1, 54, 55, 56, 57, 58, 59, 60,
61, 62, 63, 64, 65, 66, 67, -1, 69, 70,
71, 72, 73, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
121, 122, -1, 124, 1, 126, -1, 4, -1, 6,
7, 8, -1, 10, -1, 12, 13, 14, -1, 16,
-1, 18, 19, 20, -1, 22, 23, 24, 25, -1,
27, 28, 29, 30, 31, 32, 33, 34, 35, -1,
37, -1, 39, 40, 41, -1, 43, -1, -1, 46,
47, -1, 49, 50, -1, 52, -1, 54, 55, 56,
57, 58, 59, 60, 61, 62, 63, 64, 65, 66,
67, -1, 69, 70, 71, 72, 73, -1, -1, -1,
-1, -1, -1, -1, 8, -1, -1, 11, -1, -1,
-1, -1, 16, 17, 18, -1, -1, -1, 22, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
34, -1, -1, -1, 38, -1, -1, -1, -1, 43,
-1, -1, 46, 47, 121, 122, 50, 51, 52, 126,
54, 55, -1, -1, -1, 59, 60, 1, 62, -1,
4, -1, 6, -1, 8, -1, 10, -1, 12, 13,
14, -1, 16, -1, 18, 19, 20, -1, 22, 23,
24, 25, -1, 27, 28, 29, -1, -1, -1, -1,
-1, -1, -1, 37, -1, 39, 40, 41, -1, 43,
44, -1, 46, 47, -1, 49, 50, -1, 52, -1,
54, 55, -1, 57, 58, 59, 60, 121, 62, 63,
64, -1, 66, -1, -1, -1, 70, 71, 72, 73,
1, -1, -1, 4, -1, 6, -1, 8, -1, 10,
-1, 12, 13, 14, -1, 16, -1, 18, 19, 20,
-1, 22, 23, 24, 25, -1, 27, 28, 29, -1,
-1, -1, -1, -1, 108, -1, 37, -1, 39, 40,
41, -1, 43, 44, -1, 46, 47, -1, 49, 50,
-1, 52, -1, 54, 55, -1, 57, 58, 59, 60,
-1, 62, 63, 64, -1, 66, -1, -1, -1, 70,
71, 72, 73, -1, -1, -1, -1, -1, -1, 0,
1, -1, 3, 4, -1, 6, 7, 8, -1, 10,
11, 12, 13, 14, 15, 16, -1, 18, 19, 20,
-1, 22, 23, 24, 25, 106, 27, 28, 29, 30,
31, 32, 33, 34, 35, 36, 37, 38, 39, 40,
41, 42, 43, -1, 45, 46, 47, 48, 49, 50,
-1, 52, -1, 54, 55, 56, 57, 58, 59, 60,
61, 62, 63, 64, -1, 66, -1, 68, -1, 70,
71, 72, 73, -1, -1, -1, -1, -1, -1, 80,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, 1, 100,
101, 4, -1, 6, -1, 8, -1, 10, -1, 12,
13, 14, -1, 16, -1, 18, 19, 20, -1, 22,
23, 24, 25, -1, 27, 28, 29, -1, -1, -1,
-1, -1, -1, -1, 37, -1, 39, 40, 41, -1,
43, -1, -1, 46, 47, -1, 49, 50, -1, -1,
-1, 54, 55, -1, 57, 58, 59, 60, -1, 62,
63, 64, -1, 66, -1, -1, -1, 70, 71, 72,
73, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, 94, 95, 96, 97, 98, 99, 1, -1, -1,
4, -1, 6, -1, 8, -1, 10, -1, 12, 13,
14, -1, 16, -1, 18, 19, 20, -1, 22, 23,
24, 25, -1, 27, 28, 29, -1, -1, -1, -1,
-1, -1, -1, 37, -1, 39, 40, 41, -1, 43,
44, -1, 46, 47, -1, 49, 50, -1, 52, -1,
54, 55, -1, 57, 58, 59, 60, -1, 62, 63,
64, -1, 66, -1, -1, -1, 70, 71, 72, 73,
4, -1, 6, -1, 8, -1, 10, -1, 12, 13,
-1, -1, 16, 87, -1, 19, 20, -1, 22, -1,
-1, -1, -1, 27, 28, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, 39, 40, 41, -1, 43,
-1, -1, 46, -1, -1, 49, -1, -1, -1, 53,
-1, 55, -1, 57, 58, 59, 60, -1, 62, 63,
-1, -1, 66, -1, -1, -1, 70, 71, -1, 73,
-1, 4, 76, 6, -1, 8, -1, 10, -1, 12,
13, 14, -1, 16, -1, 18, 19, 20, -1, 22,
23, 24, 25, -1, 27, 28, 29, 30, 31, 32,
33, 34, 35, -1, 37, -1, 39, 40, 41, -1,
43, -1, -1, 46, 47, -1, 49, 50, -1, 52,
-1, 54, 55, -1, 57, 58, 59, 60, -1, 62,
63, 64, -1, 66, -1, -1, -1, 70, 71, 72,
73, 4, -1, 6, -1, 8, -1, 10, -1, 12,
13, -1, -1, 16, -1, -1, 19, 20, -1, 22,
-1, -1, -1, -1, 27, 28, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, 39, 40, 41, -1,
43, -1, -1, 46, -1, -1, 49, -1, -1, -1,
-1, -1, 55, -1, 57, 58, 59, 60, -1, 62,
63, -1, -1, 66, -1, -1, -1, 70, 71, -1,
73
};
#line 292 "/usr/local/lib/bison.cc"
/* fattrs + tables */
/* parser code folow */
/* This is the parser code that is written into each bison parser
when the %semantic_parser declaration is not specified in the grammar.
It was written by Richard Stallman by simplifying the hairy parser
used when %semantic_parser is specified. */
/* Note: dollar marks section change
the next is replaced by the list of actions, each action
as one case of the switch. */
#define yyerrok (yyerrstatus = 0)
#define yyclearin (YY_HTMLParser_CHAR = YYEMPTY)
#define YYEMPTY -2
#define YYEOF 0
#define YYACCEPT return(0)
#define YYABORT return(1)
#define YYERROR goto yyerrlab1
/* Like YYERROR except do call yyerror.
This remains here temporarily to ease the
transition to the new meaning of YYERROR, for GCC.
Once GCC version 2 has supplanted version 1, this can go. */
#define YYFAIL goto yyerrlab
#define YYRECOVERING() (!!yyerrstatus)
#define YYBACKUP(token, value) \
do \
if (YY_HTMLParser_CHAR == YYEMPTY && yylen == 1) \
{ YY_HTMLParser_CHAR = (token), YY_HTMLParser_LVAL = (value); \
yychar1 = YYTRANSLATE (YY_HTMLParser_CHAR); \
YYPOPSTACK; \
goto yybackup; \
} \
else \
{ YY_HTMLParser_ERROR ("syntax error: cannot back up"); YYERROR; } \
while (0)
#define YYTERROR 1
#define YYERRCODE 256
#ifndef YY_HTMLParser_PURE
/* UNPURE */
#define YYLEX YY_HTMLParser_LEX()
#ifndef YY_USE_CLASS
/* If nonreentrant, and not class , generate the variables here */
int YY_HTMLParser_CHAR; /* the lookahead symbol */
YY_HTMLParser_STYPE YY_HTMLParser_LVAL; /* the semantic value of the */
/* lookahead symbol */
int YY_HTMLParser_NERRS; /* number of parse errors so far */
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE YY_HTMLParser_LLOC; /* location data for the lookahead */
/* symbol */
#endif
#endif
#else
/* PURE */
#ifdef YY_HTMLParser_LSP_NEEDED
#define YYLEX YY_HTMLParser_LEX(&YY_HTMLParser_LVAL, &YY_HTMLParser_LLOC)
#else
#define YYLEX YY_HTMLParser_LEX(&YY_HTMLParser_LVAL)
#endif
#endif
#ifndef YY_USE_CLASS
#if YY_HTMLParser_DEBUG != 0
int YY_HTMLParser_DEBUG_FLAG; /* nonzero means print parse trace */
/* Since this is uninitialized, it does not stop multiple parsers
from coexisting. */
#endif
#endif
/* YYINITDEPTH indicates the initial size of the parser's stacks */
#ifndef YYINITDEPTH
#define YYINITDEPTH 200
#endif
/* YYMAXDEPTH is the maximum size the stacks can grow to
(effective only if the built-in stack extension method is used). */
#if YYMAXDEPTH == 0
#undef YYMAXDEPTH
#endif
#ifndef YYMAXDEPTH
#define YYMAXDEPTH 10000
#endif
#if __GNUC__ > 1 /* GNU C and GNU C++ define this. */
#define __yy_bcopy(FROM,TO,COUNT) __builtin_memcpy(TO,FROM,COUNT)
#else /* not GNU C or C++ */
/* This is the most reliable way to avoid incompatibilities
in available built-in functions on various systems. */
#ifdef __cplusplus
static void __yy_bcopy (char *from, char *to, int count)
#else
#ifdef __STDC__
static void __yy_bcopy (char *from, char *to, int count)
#else
static void __yy_bcopy (from, to, count)
char *from;
char *to;
int count;
#endif
#endif
{
register char *f = from;
register char *t = to;
register int i = count;
while (i-- > 0)
*t++ = *f++;
}
#endif
int
#ifdef YY_USE_CLASS
YY_HTMLParser_CLASS::
#endif
YY_HTMLParser_PARSE(YY_HTMLParser_PARSE_PARAM)
#ifndef __STDC__
#ifndef __cplusplus
#ifndef YY_USE_CLASS
/* parameter definition without protypes */
YY_HTMLParser_PARSE_PARAM_DEF
#endif
#endif
#endif
{
register int yystate;
register int yyn;
register short *yyssp;
register YY_HTMLParser_STYPE *yyvsp;
int yyerrstatus; /* number of tokens to shift before error messages enabled */
int yychar1; /* lookahead token as an internal (translated) token number */
short yyssa[YYINITDEPTH]; /* the state stack */
YY_HTMLParser_STYPE yyvsa[YYINITDEPTH]; /* the semantic value stack */
short *yyss = yyssa; /* refer to the stacks thru separate pointers */
YY_HTMLParser_STYPE *yyvs = yyvsa; /* to allow yyoverflow to reallocate them elsewhere */
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE yylsa[YYINITDEPTH]; /* the location stack */
YY_HTMLParser_LTYPE *yyls = yylsa;
YY_HTMLParser_LTYPE *yylsp;
#define YYPOPSTACK (yyvsp--, yyssp--, yylsp--)
#else
#define YYPOPSTACK (yyvsp--, yyssp--)
#endif
int yystacksize = YYINITDEPTH;
#ifdef YY_HTMLParser_PURE
int YY_HTMLParser_CHAR;
YY_HTMLParser_STYPE YY_HTMLParser_LVAL;
int YY_HTMLParser_NERRS;
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE YY_HTMLParser_LLOC;
#endif
#endif
YY_HTMLParser_STYPE yyval; /* the variable used to return */
/* semantic values from the action */
/* routines */
int yylen;
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Starting parse\n");
#endif
yystate = 0;
yyerrstatus = 0;
YY_HTMLParser_NERRS = 0;
YY_HTMLParser_CHAR = YYEMPTY; /* Cause a token to be read. */
/* Initialize stack pointers.
Waste one element of value and location stack
so that they stay on the same level as the state stack.
The wasted elements are never initialized. */
yyssp = yyss - 1;
yyvsp = yyvs;
#ifdef YY_HTMLParser_LSP_NEEDED
yylsp = yyls;
#endif
/* Push a new state, which is found in yystate . */
/* In all cases, when you get here, the value and location stacks
have just been pushed. so pushing a state here evens the stacks. */
yynewstate:
*++yyssp = yystate;
if (yyssp >= yyss + yystacksize - 1)
{
/* Give user a chance to reallocate the stack */
/* Use copies of these so that the &'s don't force the real ones into memory. */
YY_HTMLParser_STYPE *yyvs1 = yyvs;
short *yyss1 = yyss;
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE *yyls1 = yyls;
#endif
/* Get the current used size of the three stacks, in elements. */
int size = yyssp - yyss + 1;
#ifdef yyoverflow
/* Each stack pointer address is followed by the size of
the data in use in that stack, in bytes. */
yyoverflow("parser stack overflow",
&yyss1, size * sizeof (*yyssp),
&yyvs1, size * sizeof (*yyvsp),
#ifdef YY_HTMLParser_LSP_NEEDED
&yyls1, size * sizeof (*yylsp),
#endif
&yystacksize);
yyss = yyss1; yyvs = yyvs1;
#ifdef YY_HTMLParser_LSP_NEEDED
yyls = yyls1;
#endif
#else /* no yyoverflow */
/* Extend the stack our own way. */
if (yystacksize >= YYMAXDEPTH)
{
YY_HTMLParser_ERROR("parser stack overflow");
return 2;
}
yystacksize *= 2;
if (yystacksize > YYMAXDEPTH)
yystacksize = YYMAXDEPTH;
yyss = (short *) alloca (yystacksize * sizeof (*yyssp));
__yy_bcopy ((char *)yyss1, (char *)yyss, size * sizeof (*yyssp));
yyvs = (YY_HTMLParser_STYPE *) alloca (yystacksize * sizeof (*yyvsp));
__yy_bcopy ((char *)yyvs1, (char *)yyvs, size * sizeof (*yyvsp));
#ifdef YY_HTMLParser_LSP_NEEDED
yyls = (YY_HTMLParser_LTYPE *) alloca (yystacksize * sizeof (*yylsp));
__yy_bcopy ((char *)yyls1, (char *)yyls, size * sizeof (*yylsp));
#endif
#endif /* no yyoverflow */
yyssp = yyss + size - 1;
yyvsp = yyvs + size - 1;
#ifdef YY_HTMLParser_LSP_NEEDED
yylsp = yyls + size - 1;
#endif
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Stack size increased to %d\n", yystacksize);
#endif
if (yyssp >= yyss + yystacksize - 1)
YYABORT;
}
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Entering state %d\n", yystate);
#endif
goto yybackup;
yybackup:
/* Do appropriate processing given the current state. */
/* Read a lookahead token if we need one and don't already have one. */
/* yyresume: */
/* First try to decide what to do without reference to lookahead token. */
yyn = yypact[yystate];
if (yyn == YYFLAG)
goto yydefault;
/* Not known => get a lookahead token if don't already have one. */
/* yychar is either YYEMPTY or YYEOF
or a valid token in external form. */
if (YY_HTMLParser_CHAR == YYEMPTY)
{
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Reading a token: ");
#endif
YY_HTMLParser_CHAR = YYLEX;
}
/* Convert token to internal form (in yychar1) for indexing tables with */
if (YY_HTMLParser_CHAR <= 0) /* This means end of input. */
{
yychar1 = 0;
YY_HTMLParser_CHAR = YYEOF; /* Don't call YYLEX any more */
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Now at end of input.\n");
#endif
}
else
{
yychar1 = YYTRANSLATE(YY_HTMLParser_CHAR);
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
{
fprintf (stderr, "Next token is %d (%s", YY_HTMLParser_CHAR, yytname[yychar1]);
/* Give the individual parser a way to print the precise meaning
of a token, for further debugging info. */
#ifdef YYPRINT
YYPRINT (stderr, YY_HTMLParser_CHAR, YY_HTMLParser_LVAL);
#endif
fprintf (stderr, ")\n");
}
#endif
}
yyn += yychar1;
if (yyn < 0 || yyn > YYLAST || yycheck[yyn] != yychar1)
goto yydefault;
yyn = yytable[yyn];
/* yyn is what to do for this token type in this state.
Negative => reduce, -yyn is rule number.
Positive => shift, yyn is new state.
New state is final state => don't bother to shift,
just return success.
0, or most negative number => error. */
if (yyn < 0)
{
if (yyn == YYFLAG)
goto yyerrlab;
yyn = -yyn;
goto yyreduce;
}
else if (yyn == 0)
goto yyerrlab;
if (yyn == YYFINAL)
YYACCEPT;
/* Shift the lookahead token. */
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Shifting token %d (%s), ", YY_HTMLParser_CHAR, yytname[yychar1]);
#endif
/* Discard the token being shifted unless it is eof. */
if (YY_HTMLParser_CHAR != YYEOF)
YY_HTMLParser_CHAR = YYEMPTY;
*++yyvsp = YY_HTMLParser_LVAL;
#ifdef YY_HTMLParser_LSP_NEEDED
*++yylsp = YY_HTMLParser_LLOC;
#endif
/* count tokens shifted since error; after three, turn off error status. */
if (yyerrstatus) yyerrstatus--;
yystate = yyn;
goto yynewstate;
/* Do the default action for the current state. */
yydefault:
yyn = yydefact[yystate];
if (yyn == 0)
goto yyerrlab;
/* Do a reduction. yyn is the number of a rule to reduce with. */
yyreduce:
yylen = yyr2[yyn];
yyval = yyvsp[1-yylen]; /* implement default value of the action */
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
{
int i;
fprintf (stderr, "Reducing via rule %d (line %d), ",
yyn, yyrline[yyn]);
/* Print the symbols being reduced, and their result. */
for (i = yyprhs[yyn]; yyrhs[i] > 0; i++)
fprintf (stderr, "%s ", yytname[yyrhs[i]]);
fprintf (stderr, " -> %s\n", yytname[yyr1[yyn]]);
}
#endif
/* #line 697 "/usr/local/lib/bison.cc" */
switch (yyn) {
case 1:
#line 274 "HTMLParser.y"
{
process(*yyvsp[0].document);
delete yyvsp[0].document;
;
break;}
case 2:
#line 305 "HTMLParser.y"
{
yyval.document = new Document;
yyval.document->body.content.reset(new list >);
;
break;}
case 3:
#line 309 "HTMLParser.y"
{
yyval.document = yyvsp[-1].document;
;
break;}
case 4:
#line 312 "HTMLParser.y"
{
yyval.document = yyvsp[-1].document;
;
break;}
case 5:
#line 315 "HTMLParser.y"
{
yyval.document->attributes.reset(yyvsp[0].tag_attributes);
yyval.document = yyvsp[-1].document;
;
break;}
case 6:
#line 319 "HTMLParser.y"
{
yyval.document = yyvsp[-1].document;
;
break;}
case 7:
#line 322 "HTMLParser.y"
{
delete yyvsp[0].tag_attributes;
yyval.document = yyvsp[-1].document;
;
break;}
case 8:
#line 326 "HTMLParser.y"
{
yyval.document = yyvsp[-1].document;
;
break;}
case 9:
#line 329 "HTMLParser.y"
{
delete yyvsp[-2].tag_attributes; // Ignore attributes
(yyval.document = yyvsp[-3].document)->head.title.reset(yyvsp[-1].pcdata);
;
break;}
case 10:
#line 333 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->head.isindex_attributes.reset(yyvsp[0].tag_attributes);
;
break;}
case 11:
#line 336 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->head.base_attributes.reset(yyvsp[0].tag_attributes);
;
break;}
case 12:
#line 339 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->head.meta_attributes.reset(yyvsp[0].tag_attributes);
;
break;}
case 13:
#line 342 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->head.link_attributes.reset(yyvsp[0].tag_attributes);
;
break;}
case 14:
#line 345 "HTMLParser.y"
{
auto_ptr<Script> s(new Script);
s->attributes.reset(yyvsp[0].tag_attributes);
if (!read_cdata("</SCRIPT>", &s->text)) {
yyerror("CDATA terminal not found");
}
(yyval.document = yyvsp[-1].document)->head.scripts.push_back(s);
;
break;}
case 15:
#line 353 "HTMLParser.y"
{
auto_ptr<Style> s(new Style);
s->attributes.reset(yyvsp[0].tag_attributes);
if (!read_cdata("</STYLE>", &s->text)) {
yyerror("CDATA terminal not found");
}
(yyval.document = yyvsp[-1].document)->head.styles.push_back(s);
;
break;}
case 16:
#line 361 "HTMLParser.y"
{
delete yyvsp[0].tag_attributes;
yyval.document = yyvsp[-1].document;
;
break;}
case 17:
#line 365 "HTMLParser.y"
{
yyval.document = yyvsp[-1].document;
;
break;}
case 18:
#line 368 "HTMLParser.y"
{
Paragraph *p = new Paragraph;
p->texts.reset(yyvsp[0].element_list);
(yyval.document = yyvsp[-1].document)->body.content->push_back(auto_ptr<Element>(p));
;
break;}
case 19:
#line 373 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->body.content->push_back(auto_ptr<Element>(yyvsp[0].heading));
;
break;}
case 20:
#line 376 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->body.content->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 21:
#line 379 "HTMLParser.y"
{
(yyval.document = yyvsp[-1].document)->body.content->push_back(auto_ptr<Element>(yyvsp[0].address));
;
break;}
case 22:
#line 385 "HTMLParser.y"
{
yyval.pcdata = new PCData;
yyval.pcdata->text = *yyvsp[0].strinG;
delete yyvsp[0].strinG;
;
break;}
case 23:
#line 393 "HTMLParser.y"
{
yyval.element_list = new list<auto_ptr<Element> >;
;
break;}
case 24:
#line 396 "HTMLParser.y"
{
yyval.element_list = yyvsp[-1].element_list;
;
break;}
case 25:
#line 399 "HTMLParser.y"
{
auto_ptr<Script> s(new Script);
s->attributes.reset(yyvsp[0].tag_attributes);
if (!read_cdata("</SCRIPT>", &s->text)) {
yyerror("CDATA terminal not found");
}
// ($$ = $1)->head.scripts.push_back(s);
;
break;}
case 26:
#line 407 "HTMLParser.y"
{
auto_ptr<Style> s(new Style);
s->attributes.reset(yyvsp[0].tag_attributes);
if (!read_cdata("</STYLE>", &s->text)) {
yyerror("CDATA terminal not found");
}
// ($$ = $1)->head.styles.push_back(s);
;
break;}
case 27:
#line 415 "HTMLParser.y"
{
Paragraph *p = new Paragraph;
p->texts = auto_ptr<list<auto_ptr<Element> > >(yyvsp[0].element_list);
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(p));
;
break;}
case 28:
#line 420 "HTMLParser.y"
{
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(yyvsp[0].heading));
;
break;}
case 29:
#line 423 "HTMLParser.y"
{
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 30:
#line 426 "HTMLParser.y"
{
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(yyvsp[0].address));
;
break;}
case 31:
#line 432 "HTMLParser.y"
{
/* EXTENSION: Allow paragraph content in heading, not only texts */
if (yyvsp[-2].heading->level != yyvsp[0].inT) {
yyerror ("Levels of opening and closing headings don't match");
}
yyval.heading = yyvsp[-2].heading;
yyval.heading->content.reset(yyvsp[-1].element_list);
;
break;}
case 32:
#line 443 "HTMLParser.y"
{
yyval.element = yyvsp[0].element;
;
break;}
case 33:
#line 446 "HTMLParser.y"
{
Paragraph *p = new Paragraph;
p->attributes.reset(yyvsp[-2].tag_attributes);
p->texts.reset(yyvsp[-1].element_list);
yyval.element = p;
;
break;}
case 34:
#line 455 "HTMLParser.y"
{
yyval.element_list = new list<auto_ptr<Element> >;
;
break;}
case 35:
#line 458 "HTMLParser.y"
{
yyval.element_list = yyvsp[-1].element_list;
;
break;}
case 36:
#line 461 "HTMLParser.y"
{
yyval.element_list = yyvsp[-1].element_list;
yyval.element_list->splice(yyval.element_list->end(), *yyvsp[0].element_list);
delete yyvsp[0].element_list;
;
break;}
case 37:
#line 466 "HTMLParser.y"
{
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 38:
#line 472 "HTMLParser.y"
{
yyval.element = yyvsp[0].element;
;
break;}
case 39:
#line 475 "HTMLParser.y"
{
yyval.element = yyvsp[0].preformatted;
;
break;}
case 40:
#line 478 "HTMLParser.y"
{
yyval.element = yyvsp[0].definition_list;
;
break;}
case 41:
#line 481 "HTMLParser.y"
{
Division *p = new Division;
p->attributes.reset(yyvsp[-2].tag_attributes);
p->body_content.reset(yyvsp[-1].element_list);
yyval.element = p;
;
break;}
case 42:
#line 487 "HTMLParser.y"
{
Center *p = new Center;
delete yyvsp[-2].tag_attributes; // CENTER has no attributes.
p->body_content.reset(yyvsp[-1].element_list);
yyval.element = p;
;
break;}
case 43:
#line 493 "HTMLParser.y"
{
delete yyvsp[-2].tag_attributes; // BLOCKQUOTE has no attributes!
BlockQuote *bq = new BlockQuote;
bq->content.reset(yyvsp[-1].element_list);
yyval.element = bq;
;
break;}
case 44:
#line 499 "HTMLParser.y"
{
Form *f = new Form;
f->attributes.reset(yyvsp[-2].tag_attributes);
f->content.reset(yyvsp[-1].element_list);
yyval.element = f;
;
break;}
case 45:
#line 505 "HTMLParser.y"
{
HorizontalRule *h = new HorizontalRule;
h->attributes.reset(yyvsp[0].tag_attributes);
yyval.element = h;
;
break;}
case 46:
#line 510 "HTMLParser.y"
{
Table *t = new Table;
t->attributes.reset(yyvsp[-3].tag_attributes);
t->caption.reset(yyvsp[-2].caption);
t->rows.reset(yyvsp[-1].table_rows);
yyval.element = t;
;
break;}
case 47:
#line 520 "HTMLParser.y"
{ ++list_nesting; ;
break;}
case 48:
#line 520 "HTMLParser.y"
{
OrderedList *ol = new OrderedList;
ol->attributes.reset(yyvsp[-3].tag_attributes);
ol->items.reset(yyvsp[-1].list_items);
ol->nesting = --list_nesting;
yyval.element = ol;
;
break;}
case 49:
#line 527 "HTMLParser.y"
{ ++list_nesting; ;
break;}
case 50:
#line 527 "HTMLParser.y"
{
UnorderedList *ul = new UnorderedList;
ul->attributes.reset(yyvsp[-3].tag_attributes);
ul->items.reset(yyvsp[-1].list_items);
ul->nesting = --list_nesting;
yyval.element = ul;
;
break;}
case 51:
#line 534 "HTMLParser.y"
{ ++list_nesting; ;
break;}
case 52:
#line 534 "HTMLParser.y"
{
Dir *d = new Dir;
d->attributes.reset(yyvsp[-3].tag_attributes);
d->items.reset(yyvsp[-1].list_items);
d->nesting = --list_nesting;
yyval.element = d;
;
break;}
case 53:
#line 541 "HTMLParser.y"
{ ++list_nesting; ;
break;}
case 54:
#line 541 "HTMLParser.y"
{
Menu *m = new Menu;
m->attributes.reset(yyvsp[-3].tag_attributes);
m->items.reset(yyvsp[-1].list_items);
m->nesting = --list_nesting;
yyval.element = m;
;
break;}
case 55:
#line 551 "HTMLParser.y"
{
yyval.list_items = 0;
;
break;}
case 56:
#line 554 "HTMLParser.y"
{
yyval.list_items = yyvsp[-1].list_items;
;
break;}
case 57:
#line 557 "HTMLParser.y"
{
yyval.list_items = yyvsp[-1].list_items ? yyvsp[-1].list_items : new list<auto_ptr<ListItem> >;
yyval.list_items->push_back(auto_ptr<ListItem>(yyvsp[0].list_item));
;
break;}
case 58:
#line 564 "HTMLParser.y"
{
ListNormalItem *lni = new ListNormalItem;
lni->attributes.reset(yyvsp[-2].tag_attributes);
lni->flow.reset(yyvsp[-1].element_list);
yyval.list_item = lni;
;
break;}
case 59:
#line 570 "HTMLParser.y"
{ /* EXTENSION: Handle a "block" in a list as an indented block. */
ListBlockItem *lbi = new ListBlockItem;
lbi->block.reset(yyvsp[0].element);
yyval.list_item = lbi;
;
break;}
case 60:
#line 575 "HTMLParser.y"
{ /* EXTENSION: Treat "texts" in a list as an "<LI>". */
ListNormalItem *lni = new ListNormalItem;
lni->flow.reset(yyvsp[0].element_list);
yyval.list_item = lni;
;
break;}
case 61:
#line 585 "HTMLParser.y"
{
delete yyvsp[-4].tag_attributes;
delete yyvsp[-3].element_list; /* Kludge */
yyval.definition_list = yyvsp[-1].definition_list;
;
break;}
case 62:
#line 591 "HTMLParser.y"
{
DefinitionList *dl = new DefinitionList;
dl->attributes.reset(yyvsp[-4].tag_attributes);
dl->preamble.reset(yyvsp[-3].element_list);
dl->items.reset(yyvsp[-1].definition_list_item_list);
yyval.definition_list = dl;
;
break;}
case 63:
#line 601 "HTMLParser.y"
{
yyval.definition_list_item_list = 0;
;
break;}
case 64:
#line 604 "HTMLParser.y"
{
yyval.definition_list_item_list = yyvsp[0].definition_list_item_list;
;
break;}
case 65:
#line 607 "HTMLParser.y"
{
yyval.definition_list_item_list = yyvsp[-1].definition_list_item_list ? yyvsp[-1].definition_list_item_list : new list<auto_ptr<DefinitionListItem> >;
yyval.definition_list_item_list->push_back(auto_ptr<DefinitionListItem>(yyvsp[0].term_name));
;
break;}
case 66:
#line 611 "HTMLParser.y"
{
yyval.definition_list_item_list = yyvsp[-1].definition_list_item_list ? yyvsp[-1].definition_list_item_list : new list<auto_ptr<DefinitionListItem> >;
yyval.definition_list_item_list->push_back(auto_ptr<DefinitionListItem>(yyvsp[0].term_definition));
;
break;}
case 67:
#line 618 "HTMLParser.y"
{ /* EXTENSION: Allow "flow" instead of "texts" */
delete yyvsp[-2].tag_attributes;
yyval.term_name = new TermName;
yyval.term_name->flow.reset(yyvsp[-1].element_list);
;
break;}
case 68:
#line 623 "HTMLParser.y"
{/* EXTENSION: Ignore <P> after </DT> */
delete yyvsp[-4].tag_attributes;
delete yyvsp[-1].tag_attributes;
yyval.term_name = new TermName;
yyval.term_name->flow.reset(yyvsp[-3].element_list);
;
break;}
case 69:
#line 632 "HTMLParser.y"
{
delete yyvsp[-2].tag_attributes;
yyval.term_definition = new TermDefinition;
yyval.term_definition->flow.reset(yyvsp[-1].element_list);
;
break;}
case 70:
#line 637 "HTMLParser.y"
{/* EXTENSION: Ignore <P> after </DD> */
delete yyvsp[-4].tag_attributes;
delete yyvsp[-1].tag_attributes;
yyval.term_definition = new TermDefinition;
yyval.term_definition->flow.reset(yyvsp[-3].element_list);
;
break;}
case 71:
#line 646 "HTMLParser.y"
{
yyval.element_list = new list<auto_ptr<Element> >;
yyval.element_list->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 72:
#line 650 "HTMLParser.y"
{
yyval.element_list = yyvsp[-1].element_list;
;
break;}
case 73:
#line 653 "HTMLParser.y"
{
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 74:
#line 659 "HTMLParser.y"
{
yyval.element = yyvsp[0].element;
;
break;}
case 75:
#line 662 "HTMLParser.y"
{ /* EXTENSION: Allow headings in "flow", i.e. in lists */
yyval.element = yyvsp[0].heading;
;
break;}
case 76:
#line 665 "HTMLParser.y"
{
yyval.element = yyvsp[0].element;
;
break;}
case 77:
#line 671 "HTMLParser.y"
{
yyval.preformatted = new Preformatted;
yyval.preformatted->attributes.reset(yyvsp[-2].tag_attributes);
yyval.preformatted->texts.reset(yyvsp[-1].element_list);
;
break;}
case 78:
#line 679 "HTMLParser.y"
{
yyval.caption = new Caption;
yyval.caption->attributes.reset(yyvsp[-2].tag_attributes);
yyval.caption->texts.reset(yyvsp[-1].element_list);
;
break;}
case 79:
#line 687 "HTMLParser.y"
{
yyval.table_rows = new list<auto_ptr<TableRow> >;
;
break;}
case 80:
#line 690 "HTMLParser.y"
{
yyval.table_rows = yyvsp[-1].table_rows;
;
break;}
case 81:
#line 693 "HTMLParser.y"
{
TableRow *tr = new TableRow;
tr->attributes.reset(yyvsp[-2].tag_attributes);
tr->cells.reset(yyvsp[-1].table_cells);
(yyval.table_rows = yyvsp[-3].table_rows)->push_back(auto_ptr<TableRow>(tr));
;
break;}
case 82:
#line 702 "HTMLParser.y"
{
yyval.table_cells = new list<auto_ptr<TableCell> >;
;
break;}
case 83:
#line 705 "HTMLParser.y"
{
yyval.table_cells = yyvsp[-1].table_cells;
;
break;}
case 84:
#line 708 "HTMLParser.y"
{
TableCell *tc = new TableCell;
tc->attributes.reset(yyvsp[-2].tag_attributes);
tc->content.reset(yyvsp[-1].element_list);
(yyval.table_cells = yyvsp[-3].table_cells)->push_back(auto_ptr<TableCell>(tc));
;
break;}
case 85:
#line 714 "HTMLParser.y"
{
/* EXTENSION: Allow "</TD>" in place of "</TH>". */
TableHeadingCell *thc = new TableHeadingCell;
thc->attributes.reset(yyvsp[-3].tag_attributes);
thc->content.reset(yyvsp[-2].element_list);
(yyval.table_cells = yyvsp[-4].table_cells)->push_back(auto_ptr<TableCell>(thc));
;
break;}
case 86:
#line 721 "HTMLParser.y"
{ /* EXTENSION: Ignore <INPUT> between table cells. */
delete yyvsp[0].tag_attributes;
yyval.table_cells = yyvsp[-1].table_cells;
;
break;}
case 87:
#line 728 "HTMLParser.y"
{ /* Should be "address_content"... */
delete yyvsp[-2].tag_attributes;
yyval.address = new Address;
yyval.address->content.reset(yyvsp[-1].element_list);
;
break;}
case 88:
#line 738 "HTMLParser.y"
{
yyval.element_list = new list<auto_ptr<Element> >;
yyval.element_list->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 89:
#line 742 "HTMLParser.y"
{
(yyval.element_list = yyvsp[-1].element_list)->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 90:
#line 748 "HTMLParser.y"
{ yyval.element = yyvsp[-1].pcdata; ;
break;}
case 91:
#line 749 "HTMLParser.y"
{ yyval.element = yyvsp[-1].element; ;
break;}
case 92:
#line 750 "HTMLParser.y"
{ yyval.element = yyvsp[-1].element; ;
break;}
case 93:
#line 751 "HTMLParser.y"
{ yyval.element = yyvsp[-1].element; ;
break;}
case 94:
#line 752 "HTMLParser.y"
{ yyval.element = yyvsp[-1].element; ;
break;}
case 95:
#line 753 "HTMLParser.y"
{ /* EXTENSION: NS 1.1 / IE 2.0 */
NoBreak *nb = new NoBreak;
delete yyvsp[-3].tag_attributes;
nb->content.reset(yyvsp[-2].element_list);
yyval.element = nb;
;
break;}
case 96:
#line 762 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(TT, yyvsp[-1].element_list); ;
break;}
case 97:
#line 763 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(I, yyvsp[-1].element_list); ;
break;}
case 98:
#line 764 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(B, yyvsp[-1].element_list); ;
break;}
case 99:
#line 765 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(U, yyvsp[-1].element_list); ;
break;}
case 100:
#line 766 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(STRIKE, yyvsp[-1].element_list); ;
break;}
case 101:
#line 767 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(BIG, yyvsp[-1].element_list); ;
break;}
case 102:
#line 768 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(SMALL, yyvsp[-1].element_list); ;
break;}
case 103:
#line 769 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(SUB, yyvsp[-1].element_list); ;
break;}
case 104:
#line 770 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Font(SUP, yyvsp[-1].element_list); ;
break;}
case 105:
#line 774 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(EM, yyvsp[-1].element_list); ;
break;}
case 106:
#line 775 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(STRONG, yyvsp[-1].element_list); ;
break;}
case 107:
#line 776 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(DFN, yyvsp[-1].element_list); ;
break;}
case 108:
#line 777 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(CODE, yyvsp[-1].element_list); ;
break;}
case 109:
#line 778 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(SAMP, yyvsp[-1].element_list); ;
break;}
case 110:
#line 779 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(KBD, yyvsp[-1].element_list); ;
break;}
case 111:
#line 780 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(VAR, yyvsp[-1].element_list); ;
break;}
case 112:
#line 781 "HTMLParser.y"
{ delete yyvsp[-2].tag_attributes; yyval.element = new Phrase(CITE, yyvsp[-1].element_list); ;
break;}
case 113:
#line 788 "HTMLParser.y"
{
delete yyvsp[-2].tag_attributes;
Anchor *a = new Anchor;
a->attributes.reset(yyvsp[-3].tag_attributes);
a->texts.reset(yyvsp[-1].element_list);
yyval.element = a;
;
break;}
case 114:
#line 795 "HTMLParser.y"
{
Image *i = new Image;
i->attributes.reset(yyvsp[0].tag_attributes);
yyval.element = i;
;
break;}
case 115:
#line 800 "HTMLParser.y"
{
Applet *a = new Applet;
a->attributes.reset(yyvsp[-2].tag_attributes);
a->content.reset(yyvsp[-1].element_list);
yyval.element = a;
;
break;}
case 116:
#line 808 "HTMLParser.y"
{
Font2 *f2 = new Font2;
f2->attributes.reset(yyvsp[-2].tag_attributes);
f2->elements.reset(yyvsp[-1].element_list);
yyval.element = f2;
;
break;}
case 117:
#line 814 "HTMLParser.y"
{
BaseFont *bf = new BaseFont;
bf->attributes.reset(yyvsp[0].tag_attributes);
yyval.element = bf;
;
break;}
case 118:
#line 819 "HTMLParser.y"
{
LineBreak *lb = new LineBreak;
lb->attributes.reset(yyvsp[0].tag_attributes);
yyval.element = lb;
;
break;}
case 119:
#line 824 "HTMLParser.y"
{
Map *m = new Map;
m->attributes.reset(yyvsp[-2].tag_attributes);
m->areas.reset(yyvsp[-1].tag_attributes_list);
yyval.element = m;
;
break;}
case 120:
#line 833 "HTMLParser.y"
{
yyval.element_list = 0;
;
break;}
case 121:
#line 836 "HTMLParser.y"
{
yyval.element_list = yyvsp[-1].element_list ? yyvsp[-1].element_list : new list<auto_ptr<Element> >;
yyval.element_list->push_back(auto_ptr<Element>(yyvsp[0].element));
;
break;}
case 122:
#line 840 "HTMLParser.y"
{
yyval.element_list = yyvsp[-1].element_list ? yyvsp[-1].element_list : new list<auto_ptr<Element> >;
Param *p = new Param;
p->attributes.reset(yyvsp[0].tag_attributes);
yyval.element_list->push_back(auto_ptr<Element>(p));
;
break;}
case 123:
#line 849 "HTMLParser.y"
{
yyval.tag_attributes_list = 0;
;
break;}
case 124:
#line 852 "HTMLParser.y"
{
yyval.tag_attributes_list = yyvsp[-1].tag_attributes_list;
;
break;}
case 125:
#line 855 "HTMLParser.y"
{
yyval.tag_attributes_list = yyvsp[-1].tag_attributes_list ? yyvsp[-1].tag_attributes_list : new list<auto_ptr<list<TagAttribute> > >;
yyval.tag_attributes_list->push_back(auto_ptr<list<TagAttribute> >(yyvsp[0].tag_attributes));
;
break;}
case 126:
#line 862 "HTMLParser.y"
{
Input *i = new Input;
i->attributes.reset(yyvsp[0].tag_attributes);
yyval.element = i;
;
break;}
case 127:
#line 867 "HTMLParser.y"
{
Select *s = new Select;
s->attributes.reset(yyvsp[-2].tag_attributes);
s->content.reset(yyvsp[-1].option_list);
yyval.element = s;
;
break;}
case 128:
#line 873 "HTMLParser.y"
{
TextArea *ta = new TextArea;
ta->attributes.reset(yyvsp[-2].tag_attributes);
ta->pcdata.reset(yyvsp[-1].pcdata);
yyval.element = ta;
;
break;}
case 129:
#line 882 "HTMLParser.y"
{
yyval.option_list = new list<auto_ptr<Option> >;
yyval.option_list->push_back(auto_ptr<Option>(yyvsp[0].option));
;
break;}
case 130:
#line 886 "HTMLParser.y"
{
(yyval.option_list = yyvsp[-1].option_list)->push_back(auto_ptr<Option>(yyvsp[0].option));
;
break;}
case 131:
#line 892 "HTMLParser.y"
{
yyval.option = new Option;
yyval.option->attributes.reset(yyvsp[-2].tag_attributes);
yyval.option->pcdata.reset(yyvsp[-1].pcdata);
;
break;}
case 132:
#line 902 "HTMLParser.y"
{ yyval.heading = new Heading; yyval.heading->level = 1; yyval.heading->attributes.reset(yyvsp[0].tag_attributes); ;
break;}
case 133:
#line 903 "HTMLParser.y"
{ yyval.heading = new Heading; yyval.heading->level = 2; yyval.heading->attributes.reset(yyvsp[0].tag_attributes); ;
break;}
case 134:
#line 904 "HTMLParser.y"
{ yyval.heading = new Heading; yyval.heading->level = 3; yyval.heading->attributes.reset(yyvsp[0].tag_attributes); ;
break;}
case 135:
#line 905 "HTMLParser.y"
{ yyval.heading = new Heading; yyval.heading->level = 4; yyval.heading->attributes.reset(yyvsp[0].tag_attributes); ;
break;}
case 136:
#line 906 "HTMLParser.y"
{ yyval.heading = new Heading; yyval.heading->level = 5; yyval.heading->attributes.reset(yyvsp[0].tag_attributes); ;
break;}
case 137:
#line 907 "HTMLParser.y"
{ yyval.heading = new Heading; yyval.heading->level = 6; yyval.heading->attributes.reset(yyvsp[0].tag_attributes); ;
break;}
case 138:
#line 911 "HTMLParser.y"
{ yyval.inT = 1; ;
break;}
case 139:
#line 912 "HTMLParser.y"
{ yyval.inT = 2; ;
break;}
case 140:
#line 913 "HTMLParser.y"
{ yyval.inT = 3; ;
break;}
case 141:
#line 914 "HTMLParser.y"
{ yyval.inT = 4; ;
break;}
case 142:
#line 915 "HTMLParser.y"
{ yyval.inT = 5; ;
break;}
case 143:
#line 916 "HTMLParser.y"
{ yyval.inT = 6; ;
break;}
case 144:
#line 921 "HTMLParser.y"
{ yyval.pcdata = 0; ;
break;}
case 145:
#line 921 "HTMLParser.y"
{ yyval.pcdata = yyvsp[0].pcdata; ;
break;}
case 146:
#line 922 "HTMLParser.y"
{ yyval.caption = 0; ;
break;}
case 147:
#line 922 "HTMLParser.y"
{ yyval.caption = yyvsp[0].caption; ;
break;}
case 148:
#line 923 "HTMLParser.y"
{ yyval.element_list = 0; ;
break;}
case 149:
#line 923 "HTMLParser.y"
{ yyval.element_list = yyvsp[0].element_list; ;
break;}
case 150:
#line 924 "HTMLParser.y"
{ yyval.element_list = 0; ;
break;}
case 151:
#line 924 "HTMLParser.y"
{ yyval.element_list = yyvsp[0].element_list; ;
break;}
case 152:
#line 926 "HTMLParser.y"
{ yyval.tag_attributes = 0; ;
break;}
case 153:
#line 926 "HTMLParser.y"
{ yyval.tag_attributes = yyvsp[0].tag_attributes; ;
break;}
case 154:
#line 927 "HTMLParser.y"
{ yyval.tag_attributes = 0; ;
break;}
case 155:
#line 927 "HTMLParser.y"
{ yyval.tag_attributes = yyvsp[0].tag_attributes; ;
break;}
}
#line 697 "/usr/local/lib/bison.cc"
/* the action file gets copied in in place of this dollarsign */
yyvsp -= yylen;
yyssp -= yylen;
#ifdef YY_HTMLParser_LSP_NEEDED
yylsp -= yylen;
#endif
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
{
short *ssp1 = yyss - 1;
fprintf (stderr, "state stack now");
while (ssp1 != yyssp)
fprintf (stderr, " %d", *++ssp1);
fprintf (stderr, "\n");
}
#endif
*++yyvsp = yyval;
#ifdef YY_HTMLParser_LSP_NEEDED
yylsp++;
if (yylen == 0)
{
yylsp->first_line = YY_HTMLParser_LLOC.first_line;
yylsp->first_column = YY_HTMLParser_LLOC.first_column;
yylsp->last_line = (yylsp-1)->last_line;
yylsp->last_column = (yylsp-1)->last_column;
yylsp->text = 0;
}
else
{
yylsp->last_line = (yylsp+yylen-1)->last_line;
yylsp->last_column = (yylsp+yylen-1)->last_column;
}
#endif
/* Now "shift" the result of the reduction.
Determine what state that goes to,
based on the state we popped back to
and the rule number reduced by. */
yyn = yyr1[yyn];
yystate = yypgoto[yyn - YYNTBASE] + *yyssp;
if (yystate >= 0 && yystate <= YYLAST && yycheck[yystate] == *yyssp)
yystate = yytable[yystate];
else
yystate = yydefgoto[yyn - YYNTBASE];
goto yynewstate;
yyerrlab: /* here on detecting error */
if (! yyerrstatus)
/* If not already recovering from an error, report this error. */
{
++YY_HTMLParser_NERRS;
#ifdef YY_HTMLParser_ERROR_VERBOSE
yyn = yypact[yystate];
if (yyn > YYFLAG && yyn < YYLAST)
{
int size = 0;
char *msg;
int x, count;
count = 0;
for (x = 0; x < (sizeof(yytname) / sizeof(char *)); x++)
if (yycheck[x + yyn] == x)
size += strlen(yytname[x]) + 15, count++;
msg = (char *) malloc(size + 15);
if (msg != 0)
{
strcpy(msg, "parse error");
if (count < 5)
{
count = 0;
for (x = 0; x < (sizeof(yytname) / sizeof(char *)); x++)
if (yycheck[x + yyn] == x)
{
strcat(msg, count == 0 ? ", expecting `" : " or `");
strcat(msg, yytname[x]);
strcat(msg, "'");
count++;
}
}
YY_HTMLParser_ERROR(msg);
free(msg);
}
else
YY_HTMLParser_ERROR ("parse error; also virtual memory exceeded");
}
else
#endif /* YY_HTMLParser_ERROR_VERBOSE */
YY_HTMLParser_ERROR("parse error");
}
goto yyerrlab1;
yyerrlab1: /* here on error raised explicitly by an action */
if (yyerrstatus == 3)
{
/* if just tried and failed to reuse lookahead token after an error, discard it. */
/* return failure if at end of input */
if (YY_HTMLParser_CHAR == YYEOF)
YYABORT;
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Discarding token %d (%s).\n", YY_HTMLParser_CHAR, yytname[yychar1]);
#endif
YY_HTMLParser_CHAR = YYEMPTY;
}
/* Else will try to reuse lookahead token
after shifting the error token. */
yyerrstatus = 3; /* Each real token shifted decrements this */
goto yyerrhandle;
yyerrdefault: /* current state does not do anything special for the error token. */
#if 0
/* This is wrong; only states that explicitly want error tokens
should shift them. */
yyn = yydefact[yystate]; /* If its default is to accept any token, ok. Otherwise pop it.*/
if (yyn) goto yydefault;
#endif
yyerrpop: /* pop the current state because it cannot handle the error token */
if (yyssp == yyss) YYABORT;
yyvsp--;
yystate = *--yyssp;
#ifdef YY_HTMLParser_LSP_NEEDED
yylsp--;
#endif
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
{
short *ssp1 = yyss - 1;
fprintf (stderr, "Error: state stack now");
while (ssp1 != yyssp)
fprintf (stderr, " %d", *++ssp1);
fprintf (stderr, "\n");
}
#endif
yyerrhandle:
yyn = yypact[yystate];
if (yyn == YYFLAG)
goto yyerrdefault;
yyn += YYTERROR;
if (yyn < 0 || yyn > YYLAST || yycheck[yyn] != YYTERROR)
goto yyerrdefault;
yyn = yytable[yyn];
if (yyn < 0)
{
if (yyn == YYFLAG)
goto yyerrpop;
yyn = -yyn;
goto yyreduce;
}
else if (yyn == 0)
goto yyerrpop;
if (yyn == YYFINAL)
YYACCEPT;
#if YY_HTMLParser_DEBUG != 0
if (YY_HTMLParser_DEBUG_FLAG)
fprintf(stderr, "Shifting error token, ");
#endif
*++yyvsp = YY_HTMLParser_LVAL;
#ifdef YY_HTMLParser_LSP_NEEDED
*++yylsp = YY_HTMLParser_LLOC;
#endif
yystate = yyn;
goto yynewstate;
}
/* END */
/* #line 891 "/usr/local/lib/bison.cc" */
#line 965 "HTMLParser.y"
/* } */
/*
* Some C++ compilers (e.g. EGCS 2.91.66) have problems if all virtual
* methods of a class are inline or pure virtual, so we define the destructor,
* which is the only virtual method, non-inline, although it is empty.
*/
HTMLParser::~HTMLParser()
{
}
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/HTMLParser.h 0100644 0000000 0000000 00000027765 07525767057 014447 0 ustar root root #ifndef YY_HTMLParser_h_included
#define YY_HTMLParser_h_included
#line 1 "/usr/local/lib/bison.h"
/* before anything */
#ifdef c_plusplus
#ifndef __cplusplus
#define __cplusplus
#endif
#endif
#ifdef __cplusplus
#ifndef YY_USE_CLASS
#define YY_USE_CLASS
#endif
#else
#endif
#include <stdio.h>
/* #line 14 "/usr/local/lib/bison.h" */
#define YY_HTMLParser_PURE
#define YY_HTMLParser_DEBUG 1
#define YY_HTMLParser_LEX_BODY = 0
#define YY_HTMLParser_ERROR_BODY = 0
#define YY_HTMLParser_MEMBERS \
virtual ~HTMLParser(); \
virtual void process(const Document &) = 0;\
virtual bool read_cdata(const char *terminal, string *) = 0;\
int list_nesting;
#define YY_HTMLParser_CONSTRUCTOR_INIT : list_nesting(0)
#line 69 "HTMLParser.y"
typedef union {
Document *document;
Element *element;
list<auto_ptr<Element> > *element_list;
PCData *pcdata;
string *strinG;
list<TagAttribute> *tag_attributes;
int inT;
list<auto_ptr<TableRow> > *table_rows;
list<auto_ptr<TableCell> > *table_cells;
ListItem *list_item;
list<auto_ptr<ListItem> > *list_items;
Caption *caption;
Heading *heading;
list<auto_ptr<Option> > *option_list;
Option *option;
DefinitionList *definition_list;
list<auto_ptr<DefinitionListItem> > *definition_list_item_list;
TermName *term_name;
TermDefinition *term_definition;
Preformatted *preformatted;
Address *address;
list<auto_ptr<list<TagAttribute> > > *tag_attributes_list;
} yy_HTMLParser_stype;
#define YY_HTMLParser_STYPE yy_HTMLParser_stype
#line 14 "/usr/local/lib/bison.h"
/* %{ and %header{ and %union, during decl */
#ifndef YY_HTMLParser_COMPATIBILITY
#ifndef YY_USE_CLASS
#define YY_HTMLParser_COMPATIBILITY 1
#else
#define YY_HTMLParser_COMPATIBILITY 0
#endif
#endif
#if YY_HTMLParser_COMPATIBILITY != 0
/* backward compatibility */
#ifdef YYLTYPE
#ifndef YY_HTMLParser_LTYPE
#define YY_HTMLParser_LTYPE YYLTYPE
/* WARNING obsolete !!! user defined YYLTYPE not reported into generated header */
/* use %define LTYPE */
#endif
#endif
#ifdef YYSTYPE
#ifndef YY_HTMLParser_STYPE
#define YY_HTMLParser_STYPE YYSTYPE
/* WARNING obsolete !!! user defined YYSTYPE not reported into generated header */
/* use %define STYPE */
#endif
#endif
#ifdef YYDEBUG
#ifndef YY_HTMLParser_DEBUG
#define YY_HTMLParser_DEBUG YYDEBUG
/* WARNING obsolete !!! user defined YYDEBUG not reported into generated header */
/* use %define DEBUG */
#endif
#endif
#ifdef YY_HTMLParser_STYPE
#ifndef yystype
#define yystype YY_HTMLParser_STYPE
#endif
#endif
#endif
#ifndef YY_HTMLParser_PURE
/* #line 54 "/usr/local/lib/bison.h" */
#line 54 "/usr/local/lib/bison.h"
/* YY_HTMLParser_PURE */
#endif
/* #line 56 "/usr/local/lib/bison.h" */
#line 56 "/usr/local/lib/bison.h"
/* prefix */
#ifndef YY_HTMLParser_DEBUG
/* #line 58 "/usr/local/lib/bison.h" */
#line 58 "/usr/local/lib/bison.h"
/* YY_HTMLParser_DEBUG */
#endif
#ifndef YY_HTMLParser_LSP_NEEDED
/* #line 61 "/usr/local/lib/bison.h" */
#line 61 "/usr/local/lib/bison.h"
/* YY_HTMLParser_LSP_NEEDED*/
#endif
/* DEFAULT LTYPE*/
#ifdef YY_HTMLParser_LSP_NEEDED
#ifndef YY_HTMLParser_LTYPE
typedef
struct yyltype
{
int timestamp;
int first_line;
int first_column;
int last_line;
int last_column;
char *text;
}
yyltype;
#define YY_HTMLParser_LTYPE yyltype
#endif
#endif
/* DEFAULT STYPE*/
#ifndef YY_HTMLParser_STYPE
#define YY_HTMLParser_STYPE int
#endif
/* DEFAULT MISCELANEOUS */
#ifndef YY_HTMLParser_PARSE
#define YY_HTMLParser_PARSE yyparse
#endif
#ifndef YY_HTMLParser_LEX
#define YY_HTMLParser_LEX yylex
#endif
#ifndef YY_HTMLParser_LVAL
#define YY_HTMLParser_LVAL yylval
#endif
#ifndef YY_HTMLParser_LLOC
#define YY_HTMLParser_LLOC yylloc
#endif
#ifndef YY_HTMLParser_CHAR
#define YY_HTMLParser_CHAR yychar
#endif
#ifndef YY_HTMLParser_NERRS
#define YY_HTMLParser_NERRS yynerrs
#endif
#ifndef YY_HTMLParser_DEBUG_FLAG
#define YY_HTMLParser_DEBUG_FLAG yydebug
#endif
#ifndef YY_HTMLParser_ERROR
#define YY_HTMLParser_ERROR yyerror
#endif
#ifndef YY_HTMLParser_PARSE_PARAM
#ifndef __STDC__
#ifndef __cplusplus
#ifndef YY_USE_CLASS
#define YY_HTMLParser_PARSE_PARAM
#ifndef YY_HTMLParser_PARSE_PARAM_DEF
#define YY_HTMLParser_PARSE_PARAM_DEF
#endif
#endif
#endif
#endif
#ifndef YY_HTMLParser_PARSE_PARAM
#define YY_HTMLParser_PARSE_PARAM void
#endif
#endif
/* TOKEN C */
#ifndef YY_USE_CLASS
#ifndef YY_HTMLParser_PURE
extern YY_HTMLParser_STYPE YY_HTMLParser_LVAL;
#endif
/* #line 134 "/usr/local/lib/bison.h" */
#define DOCTYPE 258
#define PCDATA 259
#define SCAN_ERROR 260
#define A 261
#define ADDRESS 262
#define APPLET 263
#define AREA 264
#define B 265
#define BASE 266
#define BASEFONT 267
#define BIG 268
#define BLOCKQUOTE 269
#define BODY 270
#define BR 271
#define CAPTION 272
#define CENTER 273
#define CITE 274
#define CODE 275
#define DD 276
#define DFN 277
#define DIR 278
#define DIV 279
#define DL 280
#define DT 281
#define EM 282
#define FONT 283
#define FORM 284
#define H1 285
#define H2 286
#define H3 287
#define H4 288
#define H5 289
#define H6 290
#define HEAD 291
#define HR 292
#define HTML 293
#define I 294
#define IMG 295
#define INPUT 296
#define ISINDEX 297
#define KBD 298
#define LI 299
#define LINK 300
#define MAP 301
#define MENU 302
#define META 303
#define NOBR 304
#define OL 305
#define OPTION 306
#define P 307
#define PARAM 308
#define PRE 309
#define SAMP 310
#define SCRIPT 311
#define SELECT 312
#define SMALL 313
#define STRIKE 314
#define STRONG 315
#define STYLE 316
#define SUB 317
#define SUP 318
#define TABLE 319
#define TD 320
#define TEXTAREA 321
#define TH 322
#define TITLE 323
#define TR 324
#define TT 325
#define U 326
#define UL 327
#define VAR 328
#define END_A 329
#define END_ADDRESS 330
#define END_APPLET 331
#define END_B 332
#define END_BIG 333
#define END_BLOCKQUOTE 334
#define END_BODY 335
#define END_CAPTION 336
#define END_CENTER 337
#define END_CITE 338
#define END_CODE 339
#define END_DD 340
#define END_DFN 341
#define END_DIR 342
#define END_DIV 343
#define END_DL 344
#define END_DT 345
#define END_EM 346
#define END_FONT 347
#define END_FORM 348
#define END_H1 349
#define END_H2 350
#define END_H3 351
#define END_H4 352
#define END_H5 353
#define END_H6 354
#define END_HEAD 355
#define END_HTML 356
#define END_I 357
#define END_KBD 358
#define END_LI 359
#define END_MAP 360
#define END_MENU 361
#define END_NOBR 362
#define END_OL 363
#define END_OPTION 364
#define END_P 365
#define END_PRE 366
#define END_SAMP 367
#define END_SCRIPT 368
#define END_SELECT 369
#define END_SMALL 370
#define END_STRIKE 371
#define END_STRONG 372
#define END_STYLE 373
#define END_SUB 374
#define END_SUP 375
#define END_TABLE 376
#define END_TD 377
#define END_TEXTAREA 378
#define END_TH 379
#define END_TITLE 380
#define END_TR 381
#define END_TT 382
#define END_U 383
#define END_UL 384
#define END_VAR 385
#line 134 "/usr/local/lib/bison.h"
/* #defines token */
/* after #define tokens, before const tokens S5*/
#else
#ifndef YY_HTMLParser_CLASS
#define YY_HTMLParser_CLASS HTMLParser
#endif
#ifndef YY_HTMLParser_INHERIT
#define YY_HTMLParser_INHERIT
#endif
#ifndef YY_HTMLParser_MEMBERS
#define YY_HTMLParser_MEMBERS
#endif
#ifndef YY_HTMLParser_LEX_BODY
#define YY_HTMLParser_LEX_BODY
#endif
#ifndef YY_HTMLParser_ERROR_BODY
#define YY_HTMLParser_ERROR_BODY
#endif
#ifndef YY_HTMLParser_CONSTRUCTOR_PARAM
#define YY_HTMLParser_CONSTRUCTOR_PARAM
#endif
class YY_HTMLParser_CLASS YY_HTMLParser_INHERIT
{
public: /* static const int token ... */
/* #line 160 "/usr/local/lib/bison.h" */
static const int DOCTYPE;
static const int PCDATA;
static const int SCAN_ERROR;
static const int A;
static const int ADDRESS;
static const int APPLET;
static const int AREA;
static const int B;
static const int BASE;
static const int BASEFONT;
static const int BIG;
static const int BLOCKQUOTE;
static const int BODY;
static const int BR;
static const int CAPTION;
static const int CENTER;
static const int CITE;
static const int CODE;
static const int DD;
static const int DFN;
static const int DIR;
static const int DIV;
static const int DL;
static const int DT;
static const int EM;
static const int FONT;
static const int FORM;
static const int H1;
static const int H2;
static const int H3;
static const int H4;
static const int H5;
static const int H6;
static const int HEAD;
static const int HR;
static const int HTML;
static const int I;
static const int IMG;
static const int INPUT;
static const int ISINDEX;
static const int KBD;
static const int LI;
static const int LINK;
static const int MAP;
static const int MENU;
static const int META;
static const int NOBR;
static const int OL;
static const int OPTION;
static const int P;
static const int PARAM;
static const int PRE;
static const int SAMP;
static const int SCRIPT;
static const int SELECT;
static const int SMALL;
static const int STRIKE;
static const int STRONG;
static const int STYLE;
static const int SUB;
static const int SUP;
static const int TABLE;
static const int TD;
static const int TEXTAREA;
static const int TH;
static const int TITLE;
static const int TR;
static const int TT;
static const int U;
static const int UL;
static const int VAR;
static const int END_A;
static const int END_ADDRESS;
static const int END_APPLET;
static const int END_B;
static const int END_BIG;
static const int END_BLOCKQUOTE;
static const int END_BODY;
static const int END_CAPTION;
static const int END_CENTER;
static const int END_CITE;
static const int END_CODE;
static const int END_DD;
static const int END_DFN;
static const int END_DIR;
static const int END_DIV;
static const int END_DL;
static const int END_DT;
static const int END_EM;
static const int END_FONT;
static const int END_FORM;
static const int END_H1;
static const int END_H2;
static const int END_H3;
static const int END_H4;
static const int END_H5;
static const int END_H6;
static const int END_HEAD;
static const int END_HTML;
static const int END_I;
static const int END_KBD;
static const int END_LI;
static const int END_MAP;
static const int END_MENU;
static const int END_NOBR;
static const int END_OL;
static const int END_OPTION;
static const int END_P;
static const int END_PRE;
static const int END_SAMP;
static const int END_SCRIPT;
static const int END_SELECT;
static const int END_SMALL;
static const int END_STRIKE;
static const int END_STRONG;
static const int END_STYLE;
static const int END_SUB;
static const int END_SUP;
static const int END_TABLE;
static const int END_TD;
static const int END_TEXTAREA;
static const int END_TH;
static const int END_TITLE;
static const int END_TR;
static const int END_TT;
static const int END_U;
static const int END_UL;
static const int END_VAR;
#line 160 "/usr/local/lib/bison.h"
/* decl const */
public:
int YY_HTMLParser_PARSE(YY_HTMLParser_PARSE_PARAM);
virtual void YY_HTMLParser_ERROR(char *) YY_HTMLParser_ERROR_BODY;
#ifdef YY_HTMLParser_PURE
#ifdef YY_HTMLParser_LSP_NEEDED
virtual int YY_HTMLParser_LEX(YY_HTMLParser_STYPE *YY_HTMLParser_LVAL,YY_HTMLParser_LTYPE *YY_HTMLParser_LLOC) YY_HTMLParser_LEX_BODY;
#else
virtual int YY_HTMLParser_LEX(YY_HTMLParser_STYPE *YY_HTMLParser_LVAL) YY_HTMLParser_LEX_BODY;
#endif
#else
virtual int YY_HTMLParser_LEX() YY_HTMLParser_LEX_BODY;
YY_HTMLParser_STYPE YY_HTMLParser_LVAL;
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE YY_HTMLParser_LLOC;
#endif
int YY_HTMLParser_NERRS;
int YY_HTMLParser_CHAR;
#endif
#if YY_HTMLParser_DEBUG != 0
public:
int YY_HTMLParser_DEBUG_FLAG; /* nonzero means print parse trace */
#endif
public:
YY_HTMLParser_CLASS(YY_HTMLParser_CONSTRUCTOR_PARAM);
public:
YY_HTMLParser_MEMBERS
};
/* other declare folow */
#endif
#if YY_HTMLParser_COMPATIBILITY != 0
/* backward compatibility */
#ifndef YYSTYPE
#define YYSTYPE YY_HTMLParser_STYPE
#endif
#ifndef YYLTYPE
#define YYLTYPE YY_HTMLParser_LTYPE
#endif
#ifndef YYDEBUG
#ifdef YY_HTMLParser_DEBUG
#define YYDEBUG YY_HTMLParser_DEBUG
#endif
#endif
#endif
/* END */
/* #line 209 "/usr/local/lib/bison.h" */
#endif
html2text-1.3.2a/HTMLParser.k 0100644 0000000 0000000 00000027765 07525767074 014451 0 ustar root root #ifndef YY_HTMLParser_h_included
#define YY_HTMLParser_h_included
#line 1 "/usr/local/lib/bison.h"
/* before anything */
#ifdef c_plusplus
#ifndef __cplusplus
#define __cplusplus
#endif
#endif
#ifdef __cplusplus
#ifndef YY_USE_CLASS
#define YY_USE_CLASS
#endif
#else
#endif
#include <stdio.h>
/* #line 14 "/usr/local/lib/bison.h" */
#define YY_HTMLParser_PURE
#define YY_HTMLParser_DEBUG 1
#define YY_HTMLParser_LEX_BODY = 0
#define YY_HTMLParser_ERROR_BODY = 0
#define YY_HTMLParser_MEMBERS \
virtual ~HTMLParser(); \
virtual void process(const Document &) = 0;\
virtual bool read_cdata(const char *terminal, string *) = 0;\
int list_nesting;
#define YY_HTMLParser_CONSTRUCTOR_INIT : list_nesting(0)
#line 69 "HTMLParser.y"
typedef union {
Document *document;
Element *element;
list<auto_ptr<Element> > *element_list;
PCData *pcdata;
string *strinG;
list<TagAttribute> *tag_attributes;
int inT;
list<auto_ptr<TableRow> > *table_rows;
list<auto_ptr<TableCell> > *table_cells;
ListItem *list_item;
list<auto_ptr<ListItem> > *list_items;
Caption *caption;
Heading *heading;
list<auto_ptr<Option> > *option_list;
Option *option;
DefinitionList *definition_list;
list<auto_ptr<DefinitionListItem> > *definition_list_item_list;
TermName *term_name;
TermDefinition *term_definition;
Preformatted *preformatted;
Address *address;
list<auto_ptr<list<TagAttribute> > > *tag_attributes_list;
} yy_HTMLParser_stype;
#define YY_HTMLParser_STYPE yy_HTMLParser_stype
#line 14 "/usr/local/lib/bison.h"
/* %{ and %header{ and %union, during decl */
#ifndef YY_HTMLParser_COMPATIBILITY
#ifndef YY_USE_CLASS
#define YY_HTMLParser_COMPATIBILITY 1
#else
#define YY_HTMLParser_COMPATIBILITY 0
#endif
#endif
#if YY_HTMLParser_COMPATIBILITY != 0
/* backward compatibility */
#ifdef YYLTYPE
#ifndef YY_HTMLParser_LTYPE
#define YY_HTMLParser_LTYPE YYLTYPE
/* WARNING obsolete !!! user defined YYLTYPE not reported into generated header */
/* use %define LTYPE */
#endif
#endif
#ifdef YYSTYPE
#ifndef YY_HTMLParser_STYPE
#define YY_HTMLParser_STYPE YYSTYPE
/* WARNING obsolete !!! user defined YYSTYPE not reported into generated header */
/* use %define STYPE */
#endif
#endif
#ifdef YYDEBUG
#ifndef YY_HTMLParser_DEBUG
#define YY_HTMLParser_DEBUG YYDEBUG
/* WARNING obsolete !!! user defined YYDEBUG not reported into generated header */
/* use %define DEBUG */
#endif
#endif
#ifdef YY_HTMLParser_STYPE
#ifndef yystype
#define yystype YY_HTMLParser_STYPE
#endif
#endif
#endif
#ifndef YY_HTMLParser_PURE
/* #line 54 "/usr/local/lib/bison.h" */
#line 54 "/usr/local/lib/bison.h"
/* YY_HTMLParser_PURE */
#endif
/* #line 56 "/usr/local/lib/bison.h" */
#line 56 "/usr/local/lib/bison.h"
/* prefix */
#ifndef YY_HTMLParser_DEBUG
/* #line 58 "/usr/local/lib/bison.h" */
#line 58 "/usr/local/lib/bison.h"
/* YY_HTMLParser_DEBUG */
#endif
#ifndef YY_HTMLParser_LSP_NEEDED
/* #line 61 "/usr/local/lib/bison.h" */
#line 61 "/usr/local/lib/bison.h"
/* YY_HTMLParser_LSP_NEEDED*/
#endif
/* DEFAULT LTYPE*/
#ifdef YY_HTMLParser_LSP_NEEDED
#ifndef YY_HTMLParser_LTYPE
typedef
struct yyltype
{
int timestamp;
int first_line;
int first_column;
int last_line;
int last_column;
char *text;
}
yyltype;
#define YY_HTMLParser_LTYPE yyltype
#endif
#endif
/* DEFAULT STYPE*/
#ifndef YY_HTMLParser_STYPE
#define YY_HTMLParser_STYPE int
#endif
/* DEFAULT MISCELANEOUS */
#ifndef YY_HTMLParser_PARSE
#define YY_HTMLParser_PARSE yyparse
#endif
#ifndef YY_HTMLParser_LEX
#define YY_HTMLParser_LEX yylex
#endif
#ifndef YY_HTMLParser_LVAL
#define YY_HTMLParser_LVAL yylval
#endif
#ifndef YY_HTMLParser_LLOC
#define YY_HTMLParser_LLOC yylloc
#endif
#ifndef YY_HTMLParser_CHAR
#define YY_HTMLParser_CHAR yychar
#endif
#ifndef YY_HTMLParser_NERRS
#define YY_HTMLParser_NERRS yynerrs
#endif
#ifndef YY_HTMLParser_DEBUG_FLAG
#define YY_HTMLParser_DEBUG_FLAG yydebug
#endif
#ifndef YY_HTMLParser_ERROR
#define YY_HTMLParser_ERROR yyerror
#endif
#ifndef YY_HTMLParser_PARSE_PARAM
#ifndef __STDC__
#ifndef __cplusplus
#ifndef YY_USE_CLASS
#define YY_HTMLParser_PARSE_PARAM
#ifndef YY_HTMLParser_PARSE_PARAM_DEF
#define YY_HTMLParser_PARSE_PARAM_DEF
#endif
#endif
#endif
#endif
#ifndef YY_HTMLParser_PARSE_PARAM
#define YY_HTMLParser_PARSE_PARAM void
#endif
#endif
/* TOKEN C */
#ifndef YY_USE_CLASS
#ifndef YY_HTMLParser_PURE
extern YY_HTMLParser_STYPE YY_HTMLParser_LVAL;
#endif
/* #line 134 "/usr/local/lib/bison.h" */
#define DOCTYPE 258
#define PCDATA 259
#define SCAN_ERROR 260
#define A 261
#define ADDRESS 262
#define APPLET 263
#define AREA 264
#define B 265
#define BASE 266
#define BASEFONT 267
#define BIG 268
#define BLOCKQUOTE 269
#define BODY 270
#define BR 271
#define CAPTION 272
#define CENTER 273
#define CITE 274
#define CODE 275
#define DD 276
#define DFN 277
#define DIR 278
#define DIV 279
#define DL 280
#define DT 281
#define EM 282
#define FONT 283
#define FORM 284
#define H1 285
#define H2 286
#define H3 287
#define H4 288
#define H5 289
#define H6 290
#define HEAD 291
#define HR 292
#define HTML 293
#define I 294
#define IMG 295
#define INPUT 296
#define ISINDEX 297
#define KBD 298
#define LI 299
#define LINK 300
#define MAP 301
#define MENU 302
#define META 303
#define NOBR 304
#define OL 305
#define OPTION 306
#define P 307
#define PARAM 308
#define PRE 309
#define SAMP 310
#define SCRIPT 311
#define SELECT 312
#define SMALL 313
#define STRIKE 314
#define STRONG 315
#define STYLE 316
#define SUB 317
#define SUP 318
#define TABLE 319
#define TD 320
#define TEXTAREA 321
#define TH 322
#define TITLE 323
#define TR 324
#define TT 325
#define U 326
#define UL 327
#define VAR 328
#define END_A 329
#define END_ADDRESS 330
#define END_APPLET 331
#define END_B 332
#define END_BIG 333
#define END_BLOCKQUOTE 334
#define END_BODY 335
#define END_CAPTION 336
#define END_CENTER 337
#define END_CITE 338
#define END_CODE 339
#define END_DD 340
#define END_DFN 341
#define END_DIR 342
#define END_DIV 343
#define END_DL 344
#define END_DT 345
#define END_EM 346
#define END_FONT 347
#define END_FORM 348
#define END_H1 349
#define END_H2 350
#define END_H3 351
#define END_H4 352
#define END_H5 353
#define END_H6 354
#define END_HEAD 355
#define END_HTML 356
#define END_I 357
#define END_KBD 358
#define END_LI 359
#define END_MAP 360
#define END_MENU 361
#define END_NOBR 362
#define END_OL 363
#define END_OPTION 364
#define END_P 365
#define END_PRE 366
#define END_SAMP 367
#define END_SCRIPT 368
#define END_SELECT 369
#define END_SMALL 370
#define END_STRIKE 371
#define END_STRONG 372
#define END_STYLE 373
#define END_SUB 374
#define END_SUP 375
#define END_TABLE 376
#define END_TD 377
#define END_TEXTAREA 378
#define END_TH 379
#define END_TITLE 380
#define END_TR 381
#define END_TT 382
#define END_U 383
#define END_UL 384
#define END_VAR 385
#line 134 "/usr/local/lib/bison.h"
/* #defines token */
/* after #define tokens, before const tokens S5*/
#else
#ifndef YY_HTMLParser_CLASS
#define YY_HTMLParser_CLASS HTMLParser
#endif
#ifndef YY_HTMLParser_INHERIT
#define YY_HTMLParser_INHERIT
#endif
#ifndef YY_HTMLParser_MEMBERS
#define YY_HTMLParser_MEMBERS
#endif
#ifndef YY_HTMLParser_LEX_BODY
#define YY_HTMLParser_LEX_BODY
#endif
#ifndef YY_HTMLParser_ERROR_BODY
#define YY_HTMLParser_ERROR_BODY
#endif
#ifndef YY_HTMLParser_CONSTRUCTOR_PARAM
#define YY_HTMLParser_CONSTRUCTOR_PARAM
#endif
class YY_HTMLParser_CLASS YY_HTMLParser_INHERIT
{
public: /* static const int token ... */
/* #line 160 "/usr/local/lib/bison.h" */
static const int DOCTYPE;
static const int PCDATA;
static const int SCAN_ERROR;
static const int A;
static const int ADDRESS;
static const int APPLET;
static const int AREA;
static const int B;
static const int BASE;
static const int BASEFONT;
static const int BIG;
static const int BLOCKQUOTE;
static const int BODY;
static const int BR;
static const int CAPTION;
static const int CENTER;
static const int CITE;
static const int CODE;
static const int DD;
static const int DFN;
static const int DIR;
static const int DIV;
static const int DL;
static const int DT;
static const int EM;
static const int FONT;
static const int FORM;
static const int H1;
static const int H2;
static const int H3;
static const int H4;
static const int H5;
static const int H6;
static const int HEAD;
static const int HR;
static const int HTML;
static const int I;
static const int IMG;
static const int INPUT;
static const int ISINDEX;
static const int KBD;
static const int LI;
static const int LINK;
static const int MAP;
static const int MENU;
static const int META;
static const int NOBR;
static const int OL;
static const int OPTION;
static const int P;
static const int PARAM;
static const int PRE;
static const int SAMP;
static const int SCRIPT;
static const int SELECT;
static const int SMALL;
static const int STRIKE;
static const int STRONG;
static const int STYLE;
static const int SUB;
static const int SUP;
static const int TABLE;
static const int TD;
static const int TEXTAREA;
static const int TH;
static const int TITLE;
static const int TR;
static const int TT;
static const int U;
static const int UL;
static const int VAR;
static const int END_A;
static const int END_ADDRESS;
static const int END_APPLET;
static const int END_B;
static const int END_BIG;
static const int END_BLOCKQUOTE;
static const int END_BODY;
static const int END_CAPTION;
static const int END_CENTER;
static const int END_CITE;
static const int END_CODE;
static const int END_DD;
static const int END_DFN;
static const int END_DIR;
static const int END_DIV;
static const int END_DL;
static const int END_DT;
static const int END_EM;
static const int END_FONT;
static const int END_FORM;
static const int END_H1;
static const int END_H2;
static const int END_H3;
static const int END_H4;
static const int END_H5;
static const int END_H6;
static const int END_HEAD;
static const int END_HTML;
static const int END_I;
static const int END_KBD;
static const int END_LI;
static const int END_MAP;
static const int END_MENU;
static const int END_NOBR;
static const int END_OL;
static const int END_OPTION;
static const int END_P;
static const int END_PRE;
static const int END_SAMP;
static const int END_SCRIPT;
static const int END_SELECT;
static const int END_SMALL;
static const int END_STRIKE;
static const int END_STRONG;
static const int END_STYLE;
static const int END_SUB;
static const int END_SUP;
static const int END_TABLE;
static const int END_TD;
static const int END_TEXTAREA;
static const int END_TH;
static const int END_TITLE;
static const int END_TR;
static const int END_TT;
static const int END_U;
static const int END_UL;
static const int END_VAR;
#line 160 "/usr/local/lib/bison.h"
/* decl const */
public:
int YY_HTMLParser_PARSE(YY_HTMLParser_PARSE_PARAM);
virtual void YY_HTMLParser_ERROR(char *) YY_HTMLParser_ERROR_BODY;
#ifdef YY_HTMLParser_PURE
#ifdef YY_HTMLParser_LSP_NEEDED
virtual int YY_HTMLParser_LEX(YY_HTMLParser_STYPE *YY_HTMLParser_LVAL,YY_HTMLParser_LTYPE *YY_HTMLParser_LLOC) YY_HTMLParser_LEX_BODY;
#else
virtual int YY_HTMLParser_LEX(YY_HTMLParser_STYPE *YY_HTMLParser_LVAL) YY_HTMLParser_LEX_BODY;
#endif
#else
virtual int YY_HTMLParser_LEX() YY_HTMLParser_LEX_BODY;
YY_HTMLParser_STYPE YY_HTMLParser_LVAL;
#ifdef YY_HTMLParser_LSP_NEEDED
YY_HTMLParser_LTYPE YY_HTMLParser_LLOC;
#endif
int YY_HTMLParser_NERRS;
int YY_HTMLParser_CHAR;
#endif
#if YY_HTMLParser_DEBUG != 0
public:
int YY_HTMLParser_DEBUG_FLAG; /* nonzero means print parse trace */
#endif
public:
YY_HTMLParser_CLASS(YY_HTMLParser_CONSTRUCTOR_PARAM);
public:
YY_HTMLParser_MEMBERS
};
/* other declare folow */
#endif
#if YY_HTMLParser_COMPATIBILITY != 0
/* backward compatibility */
#ifndef YYSTYPE
#define YYSTYPE YY_HTMLParser_STYPE
#endif
#ifndef YYLTYPE
#define YYLTYPE YY_HTMLParser_LTYPE
#endif
#ifndef YYDEBUG
#ifdef YY_HTMLParser_DEBUG
#define YYDEBUG YY_HTMLParser_DEBUG
#endif
#endif
#endif
/* END */
/* #line 209 "/usr/local/lib/bison.h" */
#endif
html2text-1.3.2a/HTMLParser.y 0100644 0000000 0000000 00000063463 07760112171 014441 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Sun Apr 7 11:54:06 CEST 2002: Make some closing tags optional
* Mon Jul 22 13:42:13 CEST 2002: Don't insert Paragraphs to other block elements
* Mon Aug 12 17:14:57 CEST 2002: Make even more closing tags optional
*/
/***************************************************************************/
%name HTMLParser
%define PURE
%define DEBUG 1
%{
/* ------------------------------------------------------------------------- */
#ident "$Id: HTMLParser.y,v 1.14 1999/10/26 10:56:55 arno Exp $"
#include "html.h"
#include "HTMLParser.h"
// MIPS machines don't have "alloca()", so disable stack realloc'ing.
#ifdef mips
#define yyoverflow yyerror("parser stack overflow"), (void)
#endif
/* ------------------------------------------------------------------------- */
%}
/* ------------------------------------------------------------------------- */
%define LEX_BODY = 0
%define ERROR_BODY = 0
%define MEMBERS\
virtual ~HTMLParser(); \
virtual void process(const Document &) = 0;\
virtual bool read_cdata(const char *terminal, string *) = 0;\
int list_nesting;
%define CONSTRUCTOR_INIT : list_nesting(0)
%union {
Document *document;
Element *element;
list<auto_ptr<Element> > *element_list;
PCData *pcdata;
string *strinG;
list<TagAttribute> *tag_attributes;
int inT;
list<auto_ptr<TableRow> > *table_rows;
list<auto_ptr<TableCell> > *table_cells;
ListItem *list_item;
list<auto_ptr<ListItem> > *list_items;
Caption *caption;
Heading *heading;
list<auto_ptr<Option> > *option_list;
Option *option;
DefinitionList *definition_list;
list<auto_ptr<DefinitionListItem> > *definition_list_item_list;
TermName *term_name;
TermDefinition *term_definition;
Preformatted *preformatted;
Address *address;
list<auto_ptr<list<TagAttribute> > > *tag_attributes_list;
}
%type <document> document_
%type <pcdata> pcdata
%type <pcdata> opt_pcdata
%type <element_list> body_content
%type <heading> heading
%type <heading> HX
%type <inT> END_HX
%type <element> block
%type <element> block_except_p
%type <element> text
%type <element_list> texts
%type <element_list> opt_texts
%type <element> font
%type <element> phrase
%type <element> special
%type <element> form
%type <table_rows> table_rows
%type <table_cells> table_cells
%type <caption> caption
%type <caption> opt_caption
%type <element_list> applet_content
%type <definition_list> definition_list
%type <definition_list_item_list>definition_list_content
%type <term_name> term_name
%type <term_definition> term_definition
%type <option_list> select_content
%type <option> option
%type <element> list
%type <list_items> list_content
%type <list_item> list_item
%type <preformatted> preformatted
%type <element_list> opt_flow
%type <element_list> flow
%type <element> flow_
%type <element_list> paragraph_content
%type <address> address
%type <tag_attributes_list> map_content
%type <tag_attributes> opt_LI
%type <tag_attributes> opt_P
%token DOCTYPE
%token <strinG> PCDATA
%token SCAN_ERROR
%token <tag_attributes> A
%token <tag_attributes> ADDRESS
%token <tag_attributes> APPLET
%token <tag_attributes> AREA
%token <tag_attributes> B
%token <tag_attributes> BASE
%token <tag_attributes> BASEFONT
%token <tag_attributes> BIG
%token <tag_attributes> BLOCKQUOTE
%token <tag_attributes> BODY
%token <tag_attributes> BR
%token <tag_attributes> CAPTION
%token <tag_attributes> CENTER
%token <tag_attributes> CITE
%token <tag_attributes> CODE
%token <tag_attributes> DD
%token <tag_attributes> DFN
%token <tag_attributes> DIR
%token <tag_attributes> DIV
%token <tag_attributes> DL
%token <tag_attributes> DT
%token <tag_attributes> EM
%token <tag_attributes> FONT
%token <tag_attributes> FORM
%token <tag_attributes> H1
%token <tag_attributes> H2
%token <tag_attributes> H3
%token <tag_attributes> H4
%token <tag_attributes> H5
%token <tag_attributes> H6
%token <tag_attributes> HEAD
%token <tag_attributes> HR
%token <tag_attributes> HTML
%token <tag_attributes> I
%token <tag_attributes> IMG
%token <tag_attributes> INPUT
%token <tag_attributes> ISINDEX
%token <tag_attributes> KBD
%token <tag_attributes> LI
%token <tag_attributes> LINK
%token <tag_attributes> MAP
%token <tag_attributes> MENU
%token <tag_attributes> META
%token <tag_attributes> NOBR
%token <tag_attributes> OL
%token <tag_attributes> OPTION
%token <tag_attributes> P
%token <tag_attributes> PARAM
%token <tag_attributes> PRE
%token <tag_attributes> SAMP
%token <tag_attributes> SCRIPT
%token <tag_attributes> SELECT
%token <tag_attributes> SMALL
%token <tag_attributes> STRIKE
%token <tag_attributes> STRONG
%token <tag_attributes> STYLE
%token <tag_attributes> SUB
%token <tag_attributes> SUP
%token <tag_attributes> TABLE
%token <tag_attributes> TD
%token <tag_attributes> TEXTAREA
%token <tag_attributes> TH
%token <tag_attributes> TITLE
%token <tag_attributes> TR
%token <tag_attributes> TT
%token <tag_attributes> U
%token <tag_attributes> UL
%token <tag_attributes> VAR
%token END_A
%token END_ADDRESS
%token END_APPLET
%token END_B
%token END_BIG
%token END_BLOCKQUOTE
%token END_BODY
%token END_CAPTION
%token END_CENTER
%token END_CITE
%token END_CODE
%token END_DD
%token END_DFN
%token END_DIR
%token END_DIV
%token END_DL
%token END_DT
%token END_EM
%token END_FONT
%token END_FORM
%token END_H1
%token END_H2
%token END_H3
%token END_H4
%token END_H5
%token END_H6
%token END_HEAD
%token END_HTML
%token END_I
%token END_KBD
%token END_LI
%token END_MAP
%token END_MENU
%token END_NOBR
%token END_OL
%token END_OPTION
%token END_P
%token END_PRE
%token END_SAMP
%token END_SCRIPT
%token END_SELECT
%token END_SMALL
%token END_STRIKE
%token END_STRONG
%token END_STYLE
%token END_SUB
%token END_SUP
%token END_TABLE
%token END_TD
%token END_TEXTAREA
%token END_TH
%token END_TITLE
%token END_TR
%token END_TT
%token END_U
%token END_UL
%token END_VAR
/* ------------------------------------------------------------------------- */
%start document
%% /* { */
document:
document_ {
process(*$1);
delete $1;
}
;
/*
* Well... actually, an HTML document should look like
*
* <!DOCTYPE ...>
* <HTML>
* <HEAD>
* ...
* </HEAD>
* <BODY>
* ...
* </BODY>
* </HTML>
*
* but...
*
* (A) All seven tags are optional
* (B) The contents of the HEAD and the BODY section can be distinuished
* (C) Most people out there do not know which element to put before, into,
* or after which section...
*
* so... let's just forget about the structure of an HTML document, discard
* the seven tags, and process the remainder as a series of sections.
*/
document_:
/* empty */ {
$$ = new Document;
$$->body.content.reset(new list<auto_ptr<Element> >);
}
| document_ error {
$$ = $1;
}
| document_ DOCTYPE {
$$ = $1;
}
| document_ HTML {
$$->attributes.reset($2);
$$ = $1;
}
| document_ END_HTML {
$$ = $1;
}
| document_ HEAD {
delete $2;
$$ = $1;
}
| document_ END_HEAD {
$$ = $1;
}
| document_ TITLE opt_pcdata opt_END_TITLE {
delete $2; // Ignore <TITLE> attributes
($$ = $1)->head.title.reset($3);
}
| document_ ISINDEX {
($$ = $1)->head.isindex_attributes.reset($2);
}
| document_ BASE {
($$ = $1)->head.base_attributes.reset($2);
}
| document_ META {
($$ = $1)->head.meta_attributes.reset($2);
}
| document_ LINK {
($$ = $1)->head.link_attributes.reset($2);
}
| document_ SCRIPT {
auto_ptr<Script> s(new Script);
s->attributes.reset($2);
if (!read_cdata("</SCRIPT>", &s->text)) {
yyerror("CDATA terminal not found");
}
($$ = $1)->head.scripts.push_back(s);
}
| document_ STYLE {
auto_ptr<Style> s(new Style);
s->attributes.reset($2);
if (!read_cdata("</STYLE>", &s->text)) {
yyerror("CDATA terminal not found");
}
($$ = $1)->head.styles.push_back(s);
}
| document_ BODY {
delete $2;
$$ = $1;
}
| document_ END_BODY {
$$ = $1;
}
| document_ texts {
Paragraph *p = new Paragraph;
p->texts.reset($2);
($$ = $1)->body.content->push_back(auto_ptr<Element>(p));
}
| document_ heading {
($$ = $1)->body.content->push_back(auto_ptr<Element>($2));
}
| document_ block {
($$ = $1)->body.content->push_back(auto_ptr<Element>($2));
}
| document_ address {
($$ = $1)->body.content->push_back(auto_ptr<Element>($2));
}
;
pcdata:
PCDATA {
$$ = new PCData;
$$->text = *$1;
delete $1;
}
;
body_content:
/* empty */ {
$$ = new list<auto_ptr<Element> >;
}
| body_content error {
$$ = $1;
}
| body_content SCRIPT {
auto_ptr<Script> s(new Script);
s->attributes.reset($2);
if (!read_cdata("</SCRIPT>", &s->text)) {
yyerror("CDATA terminal not found");
}
// ($$ = $1)->head.scripts.push_back(s);
}
| body_content STYLE {
auto_ptr<Style> s(new Style);
s->attributes.reset($2);
if (!read_cdata("</STYLE>", &s->text)) {
yyerror("CDATA terminal not found");
}
// ($$ = $1)->head.styles.push_back(s);
}
| body_content texts {
Paragraph *p = new Paragraph;
p->texts = auto_ptr<list<auto_ptr<Element> > >($2);
($$ = $1)->push_back(auto_ptr<Element>(p));
}
| body_content heading {
($$ = $1)->push_back(auto_ptr<Element>($2));
}
| body_content block {
($$ = $1)->push_back(auto_ptr<Element>($2));
}
| body_content address {
($$ = $1)->push_back(auto_ptr<Element>($2));
}
;
heading:
HX paragraph_content END_HX {
/* EXTENSION: Allow paragraph content in heading, not only texts */
if ($1->level != $3) {
yyerror ("Levels of opening and closing headings don't match");
}
$$ = $1;
$$->content.reset($2);
}
;
block:
block_except_p {
$$ = $1;
}
| P paragraph_content opt_END_P {
Paragraph *p = new Paragraph;
p->attributes.reset($1);
p->texts.reset($2);
$$ = p;
}
;
paragraph_content: /* EXTENSION: Allow blocks (except "<P>") in paragraphs. */
/* empty */ {
$$ = new list<auto_ptr<Element> >;
}
| paragraph_content error {
$$ = $1;
}
| paragraph_content texts {
$$ = $1;
$$->splice($$->end(), *$2);
delete $2;
}
| paragraph_content block_except_p {
($$ = $1)->push_back(auto_ptr<Element>($2));
}
;
block_except_p:
list {
$$ = $1;
}
| preformatted {
$$ = $1;
}
| definition_list {
$$ = $1;
}
| DIV body_content opt_END_DIV {
Division *p = new Division;
p->attributes.reset($1);
p->body_content.reset($2);
$$ = p;
}
| CENTER body_content opt_END_CENTER {
Center *p = new Center;
delete $1; // CENTER has no attributes.
p->body_content.reset($2);
$$ = p;
}
| BLOCKQUOTE body_content opt_END_BLOCKQUOTE {
delete $1; // BLOCKQUOTE has no attributes!
BlockQuote *bq = new BlockQuote;
bq->content.reset($2);
$$ = bq;
}
| FORM body_content opt_END_FORM {
Form *f = new Form;
f->attributes.reset($1);
f->content.reset($2);
$$ = f;
}
| HR {
HorizontalRule *h = new HorizontalRule;
h->attributes.reset($1);
$$ = h;
}
| TABLE opt_caption table_rows END_TABLE {
Table *t = new Table;
t->attributes.reset($1);
t->caption.reset($2);
t->rows.reset($3);
$$ = t;
}
;
list:
OL { ++list_nesting; } list_content END_OL {
OrderedList *ol = new OrderedList;
ol->attributes.reset($1);
ol->items.reset($3);
ol->nesting = --list_nesting;
$$ = ol;
}
| UL { ++list_nesting; } list_content opt_END_UL {
UnorderedList *ul = new UnorderedList;
ul->attributes.reset($1);
ul->items.reset($3);
ul->nesting = --list_nesting;
$$ = ul;
}
| DIR { ++list_nesting; } list_content END_DIR {
Dir *d = new Dir;
d->attributes.reset($1);
d->items.reset($3);
d->nesting = --list_nesting;
$$ = d;
}
| MENU { ++list_nesting; } list_content END_MENU {
Menu *m = new Menu;
m->attributes.reset($1);
m->items.reset($3);
m->nesting = --list_nesting;
$$ = m;
}
;
list_content:
/* empty */ {
$$ = 0;
}
| list_content error {
$$ = $1;
}
| list_content list_item {
$$ = $1 ? $1 : new list<auto_ptr<ListItem> >;
$$->push_back(auto_ptr<ListItem>($2));
}
;
list_item:
LI opt_flow opt_END_LI {
ListNormalItem *lni = new ListNormalItem;
lni->attributes.reset($1);
lni->flow.reset($2);
$$ = lni;
}
| block { /* EXTENSION: Handle a "block" in a list as an indented block. */
ListBlockItem *lbi = new ListBlockItem;
lbi->block.reset($1);
$$ = lbi;
}
| texts { /* EXTENSION: Treat "texts" in a list as an "<LI>". */
ListNormalItem *lni = new ListNormalItem;
lni->flow.reset($1);
$$ = lni;
}
;
definition_list:
/* EXTENSION: Allow nested <DL>s. */
/* EXTENSION: "</DL>" optional. */
DL opt_flow opt_error definition_list opt_END_DL {
delete $1;
delete $2; /* Kludge */
$$ = $4;
}
/* EXTENSION: Accept a "preamble" in the DL */
| DL opt_flow opt_error definition_list_content END_DL {
DefinitionList *dl = new DefinitionList;
dl->attributes.reset($1);
dl->preamble.reset($2);
dl->items.reset($4);
$$ = dl;
}
;
definition_list_content:
/* empty */ {
$$ = 0;
}
| definition_list_content {
$$ = $1;
}
| definition_list_content term_name {
$$ = $1 ? $1 : new list<auto_ptr<DefinitionListItem> >;
$$->push_back(auto_ptr<DefinitionListItem>($2));
}
| definition_list_content term_definition {
$$ = $1 ? $1 : new list<auto_ptr<DefinitionListItem> >;
$$->push_back(auto_ptr<DefinitionListItem>($2));
}
;
term_name:
DT opt_flow opt_error { /* EXTENSION: Allow "flow" instead of "texts" */
delete $1;
$$ = new TermName;
$$->flow.reset($2);
}
| DT opt_flow END_DT opt_P opt_error {/* EXTENSION: Ignore <P> after </DT> */
delete $1;
delete $4;
$$ = new TermName;
$$->flow.reset($2);
}
;
term_definition:
DD opt_flow opt_error {
delete $1;
$$ = new TermDefinition;
$$->flow.reset($2);
}
| DD opt_flow END_DD opt_P opt_error {/* EXTENSION: Ignore <P> after </DD> */
delete $1;
delete $4;
$$ = new TermDefinition;
$$->flow.reset($2);
}
;
flow:
flow_ {
$$ = new list<auto_ptr<Element> >;
$$->push_back(auto_ptr<Element>($1));
}
| flow error {
$$ = $1;
}
| flow flow_ {
($$ = $1)->push_back(auto_ptr<Element>($2));
}
;
flow_:
text {
$$ = $1;
}
| heading { /* EXTENSION: Allow headings in "flow", i.e. in lists */
$$ = $1;
}
| block {
$$ = $1;
}
;
preformatted:
PRE opt_texts opt_END_PRE {
$$ = new Preformatted;
$$->attributes.reset($1);
$$->texts.reset($2);
}
;
caption:
CAPTION opt_texts END_CAPTION {
$$ = new Caption;
$$->attributes.reset($1);
$$->texts.reset($2);
}
;
table_rows:
/* empty */ {
$$ = new list<auto_ptr<TableRow> >;
}
| table_rows error {
$$ = $1;
}
| table_rows TR table_cells opt_END_TR {
TableRow *tr = new TableRow;
tr->attributes.reset($2);
tr->cells.reset($3);
($$ = $1)->push_back(auto_ptr<TableRow>(tr));
}
;
table_cells:
/* empty */ {
$$ = new list<auto_ptr<TableCell> >;
}
| table_cells error {
$$ = $1;
}
| table_cells TD body_content opt_END_TD {
TableCell *tc = new TableCell;
tc->attributes.reset($2);
tc->content.reset($3);
($$ = $1)->push_back(auto_ptr<TableCell>(tc));
}
| table_cells TH body_content opt_END_TH opt_END_TD {
/* EXTENSION: Allow "</TD>" in place of "</TH>". */
TableHeadingCell *thc = new TableHeadingCell;
thc->attributes.reset($2);
thc->content.reset($3);
($$ = $1)->push_back(auto_ptr<TableCell>(thc));
}
| table_cells INPUT { /* EXTENSION: Ignore <INPUT> between table cells. */
delete $2;
$$ = $1;
}
;
address:
ADDRESS opt_texts END_ADDRESS { /* Should be "address_content"... */
delete $1;
$$ = new Address;
$$->content.reset($2);
}
;
/* ------------------------------------------------------------------------- */
texts:
text {
$$ = new list<auto_ptr<Element> >;
$$->push_back(auto_ptr<Element>($1));
}
| texts text {
($$ = $1)->push_back(auto_ptr<Element>($2));
}
;
text:
pcdata opt_error { $$ = $1; }
| font opt_error { $$ = $1; }
| phrase opt_error { $$ = $1; }
| special opt_error { $$ = $1; }
| form opt_error { $$ = $1; }
| NOBR opt_texts END_NOBR opt_error { /* EXTENSION: NS 1.1 / IE 2.0 */
NoBreak *nb = new NoBreak;
delete $1;
nb->content.reset($2);
$$ = nb;
}
;
font:
TT opt_texts opt_END_TT { delete $1; $$ = new Font(TT, $2); }
| I opt_texts opt_END_I { delete $1; $$ = new Font(I, $2); }
| B opt_texts opt_END_B { delete $1; $$ = new Font(B, $2); }
| U opt_texts opt_END_U { delete $1; $$ = new Font(U, $2); }
| STRIKE opt_texts opt_END_STRIKE { delete $1; $$ = new Font(STRIKE, $2); }
| BIG opt_texts opt_END_BIG { delete $1; $$ = new Font(BIG, $2); }
| SMALL opt_texts opt_END_SMALL { delete $1; $$ = new Font(SMALL, $2); }
| SUB opt_texts opt_END_SUB { delete $1; $$ = new Font(SUB, $2); }
| SUP opt_texts opt_END_SUP { delete $1; $$ = new Font(SUP, $2); }
;
phrase:
EM opt_texts opt_END_EM { delete $1; $$ = new Phrase(EM, $2); }
| STRONG opt_texts opt_END_STRONG { delete $1; $$ = new Phrase(STRONG, $2); }
| DFN opt_texts opt_END_DFN { delete $1; $$ = new Phrase(DFN, $2); }
| CODE opt_texts opt_END_CODE { delete $1; $$ = new Phrase(CODE, $2); }
| SAMP opt_texts opt_END_SAMP { delete $1; $$ = new Phrase(SAMP, $2); }
| KBD opt_texts opt_END_KBD { delete $1; $$ = new Phrase(KBD, $2); }
| VAR opt_texts opt_END_VAR { delete $1; $$ = new Phrase(VAR, $2); }
| CITE opt_texts opt_END_CITE { delete $1; $$ = new Phrase(CITE, $2); }
;
special:
/* EXTENSION: Allow "flow" in <A>, not only "texts". */
/* EXTENSION: Allow useless <LI> in anchor. */
/* EXTENSION: "</A>" optional.*/
A opt_LI opt_flow opt_END_A {
delete $2;
Anchor *a = new Anchor;
a->attributes.reset($1);
a->texts.reset($3);
$$ = a;
}
| IMG {
Image *i = new Image;
i->attributes.reset($1);
$$ = i;
}
| APPLET applet_content END_APPLET {
Applet *a = new Applet;
a->attributes.reset($1);
a->content.reset($2);
$$ = a;
}
/* EXTENSION: "flow" in <FONT> allowed, not only "texts". */
/* EXTENSION: "</FONT>" optional. */
| FONT opt_flow opt_END_FONT {
Font2 *f2 = new Font2;
f2->attributes.reset($1);
f2->elements.reset($2);
$$ = f2;
}
| BASEFONT {
BaseFont *bf = new BaseFont;
bf->attributes.reset($1);
$$ = bf;
}
| BR {
LineBreak *lb = new LineBreak;
lb->attributes.reset($1);
$$ = lb;
}
| MAP map_content END_MAP {
Map *m = new Map;
m->attributes.reset($1);
m->areas.reset($2);
$$ = m;
}
;
applet_content:
/* empty */ {
$$ = 0;
}
| applet_content text {
$$ = $1 ? $1 : new list<auto_ptr<Element> >;
$$->push_back(auto_ptr<Element>($2));
}
| applet_content PARAM {
$$ = $1 ? $1 : new list<auto_ptr<Element> >;
Param *p = new Param;
p->attributes.reset($2);
$$->push_back(auto_ptr<Element>(p));
}
;
map_content:
/* empty */ {
$$ = 0;
}
| map_content error {
$$ = $1;
}
| map_content AREA {
$$ = $1 ? $1 : new list<auto_ptr<list<TagAttribute> > >;
$$->push_back(auto_ptr<list<TagAttribute> >($2));
}
;
form:
INPUT {
Input *i = new Input;
i->attributes.reset($1);
$$ = i;
}
| SELECT select_content END_SELECT {
Select *s = new Select;
s->attributes.reset($1);
s->content.reset($2);
$$ = s;
}
| TEXTAREA pcdata END_TEXTAREA {
TextArea *ta = new TextArea;
ta->attributes.reset($1);
ta->pcdata.reset($2);
$$ = ta;
}
;
select_content:
option {
$$ = new list<auto_ptr<Option> >;
$$->push_back(auto_ptr<Option>($1));
}
| select_content option {
($$ = $1)->push_back(auto_ptr<Option>($2));
}
;
option:
OPTION pcdata opt_END_OPTION {
$$ = new Option;
$$->attributes.reset($1);
$$->pcdata.reset($2);
}
;
/* ------------------------------------------------------------------------- */
HX:
H1 { $$ = new Heading; $$->level = 1; $$->attributes.reset($1); }
| H2 { $$ = new Heading; $$->level = 2; $$->attributes.reset($1); }
| H3 { $$ = new Heading; $$->level = 3; $$->attributes.reset($1); }
| H4 { $$ = new Heading; $$->level = 4; $$->attributes.reset($1); }
| H5 { $$ = new Heading; $$->level = 5; $$->attributes.reset($1); }
| H6 { $$ = new Heading; $$->level = 6; $$->attributes.reset($1); }
;
END_HX:
END_H1 { $$ = 1; }
| END_H2 { $$ = 2; }
| END_H3 { $$ = 3; }
| END_H4 { $$ = 4; }
| END_H5 { $$ = 5; }
| END_H6 { $$ = 6; }
;
/* ------------------------------------------------------------------------- */
opt_pcdata: /* empty */ { $$ = 0; } | pcdata { $$ = $1; };
opt_caption: /* empty */ { $$ = 0; } | caption { $$ = $1; };
opt_texts: /* empty */ { $$ = 0; } | texts { $$ = $1; };
opt_flow: /* empty */ { $$ = 0; } | flow { $$ = $1; };
opt_LI: /* empty */ { $$ = 0; } | LI { $$ = $1; };
opt_P: /* empty */ { $$ = 0; } | P { $$ = $1; };
opt_END_A: /* empty */ | END_A;
opt_END_B: /* empty */ | END_B;
opt_END_BLOCKQUOTE: /* empty */ | END_BLOCKQUOTE;
opt_END_BIG: /* empty */ | END_BIG;
opt_END_CENTER: /* empty */ | END_CENTER;
opt_END_CITE: /* empty */ | END_CITE;
opt_END_CODE: /* empty */ | END_CODE;
opt_END_DFN: /* empty */ | END_DFN;
opt_END_DIV: /* empty */ | END_DIV;
opt_END_DL: /* empty */ | END_DL;
opt_END_EM: /* empty */ | END_EM;
opt_END_FONT: /* empty */ | END_FONT;
opt_END_FORM: /* empty */ | END_FORM;
opt_END_I: /* empty */ | END_I;
opt_END_KBD: /* empty */ | END_KBD;
opt_END_LI: /* empty */ | END_LI;
opt_END_OPTION: /* empty */ | END_OPTION;
opt_END_P: /* empty */ | END_P;
opt_END_PRE: /* empty */ | END_PRE;
opt_END_SAMP: /* empty */ | END_SAMP;
opt_END_SMALL: /* empty */ | END_SMALL;
opt_END_STRIKE: /* empty */ | END_STRIKE;
opt_END_STRONG: /* empty */ | END_STRONG;
opt_END_SUB: /* empty */ | END_SUB;
opt_END_SUP: /* empty */ | END_SUP;
opt_END_TD: /* empty */ | END_TD;
opt_END_TH: /* empty */ | END_TH;
opt_END_TITLE: /* empty */ | END_TITLE;
opt_END_TR: /* empty */ | END_TR;
opt_END_TT: /* empty */ | END_TT;
opt_END_U: /* empty */ | END_U;
opt_END_UL: /* empty */ | END_UL;
opt_END_VAR: /* empty */ | END_VAR;
opt_error: /* empty */ | error;
%% /* } */
/*
* Some C++ compilers (e.g. EGCS 2.91.66) have problems if all virtual
* methods of a class are inline or pure virtual, so we define the destructor,
* which is the only virtual method, non-inline, although it is empty.
*/
HTMLParser::~HTMLParser()
{
}
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/INSTALL 0100644 0000000 0000000 00000017306 07534114105 013350 0 ustar root root ## INSTALL - How to compile and install Sat Aug 31 12:04:42 CEST 2002
## ===========================================================================
#
# For the impatient:
'cd' into the html2text distribution directory
./configure (in some shells 'sh ./configure')
make (or in some cases 'gmake')
'mv' the html2text executable to its installation directory (e.g. /usr/local/bin)
## ---------------------------------------------------------------------------
#
# html2text can be compiled on many UNIX-like platforms, in particular those
# that provide a GNU compiler (g++).
1. Untar the distribution package:
$ gunzip html2text-1.3.X.tar.gz
$ tar xf html2text-1.3.X.tar
2. Change into the html2text distribution directory:
$ cd html2text-1.3.X
3. To generate the make files, issue:
$ ./configure
If you're using a csh on an old version of System V, you might need to type
'sh ./configure' to prevent the csh from trying to execute 'configure'
itself.
While the script is running, it prints some messages telling which features
it is checking for, alike (the exact output depends on your platform):
| Checking C++ compiler... use "g++"
| Checking <sys/poll.h>... OK
| Checking for socket libraries... no extra libraries required
| Checking "bool"... built-in
| Checking "explicit"... built-in
| Checking Standard C++ library... works; no need to make "./libstd"
| Checking "auto_ptr"... not defined or not working, use
| "./libstd/include/auto_ptr.h"
| Checking "makedepend" includes... use "-I/usr/include -I/usr/include/bits
| -I/usr/include/g++ -I/usr/include/gnu -I/usr/include/sys
| -I/usr/lib/gcc-lib/i486-suse-linux/2.95.3/include "
| Creating "./Makefile" from "./Makefile.in"... done
|
| Preparing completed. You may now run "make" (or "gmake").
4. Then compile html2text with:
$ make
On non-GNU systems and/or if 'make' fails, you might need to use
'gmake' instead of 'make', in order to force a compilation by g++.
Compiling 'html2text' takes awhile. While 'make' is running, it will print
some messages (and, hopefully, no errors), alike:
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g html2text.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g html.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g HTMLControl.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g HTMLParser.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g Area.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g format.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g sgml.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g table.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g urlistream.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g Properties.C
| g++ -c -DVERSION=1.3.1 -DAUTO_PTR_BROKEN -O2 -g cmp_nocase.C
| g++ -O2 -g html2text.o html.o HTMLControl.o HTMLParser.o Area.o format.o
| sgml.o table.o urlistream.o Properties.o cmp_nocase.o -o html2text
|
| Compilation completed. You may now move "html2text", "html2text.1.gz"
| and "html2textrc.5.gz" to their installation directories (e.g.
| "/usr/local/bin", "/usr/local/man/man1" and "/usr/local/man/man5").
5. No automatic installation is provided by now.
Be root. Then move the html2text executable and the manual pages to their
respective installation directories (e.g. /usr/local/bin, /usr/local/man/man1
and /usr/local/man/man5). Be sure you set the execution rights accordingly
and the files are owned by root or whoever owns binaries on your system. E.g.:
# install -s -m 755 html2text /usr/local/bin
# install -m 644 html2text.1.gz /usr/local/man/man1
# install -m 644 html2textrc.5.gz /usr/local/man/man5
After this, create a directory for the documentation files at an appropriate
place (e.g. /usr/doc/html2text or /usr/share/doc/html2text), and move all
documentation files into that folder. E.g.:
# install -d -m 755 /usr/share/doc/html2text
# install -b -p -m 644 *[ABD-Z] /usr/share/doc/html2text
Be sure you read the README file!
## ---------------------------------------------------------------------------
#
# If you prefer to install the program as an RPM package:
Place the orginal source tarball to rpm's build directory, e.g.
/usr/src/packages/SOURCES
Then, download the spec file from the program's homepage and start the build
with the command
rpm -bb html2text.spec
After successfull compilation, rpm will print a message like
| Wrote: /usr/src/packages/RPMS/i386/html2text-1.3.1-1.i386.rpm
This package can now be installed with rpm, e.g.
rpm -Uhv /usr/src/packages/RPMS/i386/html2text-1.3.1-1.i386.rpm
## ===========================================================================
#
# Hints for porting html2text to other platforms and for solving other problems:
On g++ version 3, the 'istream.h' header file from the compiler's 'backward'
directory is used. You might need to point to that directory in the Makefile's
line beginning with 'LIBSTDCXX_INCLUDES', e.g.
LIBSTDCXX_INCLUDES = -I/usr/local/include/g++-v3/backward
Some compilers have weird built-in rules which collide with the rules in the
make files. If 'make' fails, then try to disable the built-in rules. For most
'make' utilities, this can be achieved by specifying the '-r' command line
option, i.e. 'make -r'.
From version 1.02, html2text requires the "socket()" function and its
friends, which live in different libraries for the different systems.
"configure" tries several sets of "-l" linker options to find the right
libraries.
Some C++ compilers lack a built-in "bool" data type. "configure" attempts to
find a suitable definition which it passes to the compiler with
"-DBOOL_DEFINITION=...".
html2text requires a standard C++ library. Since some old C++ compilers do
not come with a standard C++ library, I have implemented parts of the library
in the 'libstd' subdirectory; the exported header files are in
'libstd/include'. For platforms which come with a (working) standard C++
library, the "home-grown" library in 'libstd' is not compiled and linked.
However, on some platforms, these librarys did not work. I don't know if this
because the compiler or our 'libstd' library is broken, or because we have
some syntax errors in the source code files.
Some old GNU Standard C++ Library versions falsely re-names "list::erase()"
as "list::remove()". I fixed this with a "-DSTRING_ERASE=remove" on the "g++"
command line.
Some compilers do come with a Standard C++ Library, but the definition of the
"auto_ptr" template is missing from "<memory>", or is not standard-compliant.
This condition is checked by "configure" and "./libstd/include/auto_ptr.h" is
included if necessary (preprocessor symbol "HAS_WORKING_AUTO_PTR").
"make depend" attempts to run the MAKEDEPEND utility (not included in this
package). Unfortunately, most C++ compilers implicitly use some "secret"
include directories, which MAKEDEPEND doesn't know of; as a result,
MAKEDEPEND may issue some "could not find..." errors, which shouldn't worry
you. The "configure" script attempts to guess the "secret include directory"
and passes it with "-I" to MAKEDEPEND.
To generate 'HTMLParser.C' and 'HTMLParser.h' from 'HTMLParser.y' and
'HTMLParker.k' (which can be archived with the 'make bison-local' directive),
you need bison++ version 2.2, written by Alain Coetmeur. Unfortunately, this
version is completely outdated and thus not longer being maintained or
supported in any way. As you will need it if you want to hack into the program,
you can find the program's sources on html2text's homepage.
However, the already generated 'HTMLParser.C' and 'HTMLParser.h' files are
included into html2text's source code package, enableing anybody to compile
html2text without having to install bison++-2.2 before.
## ===========================================================================
Martin Bayer <mbayer@zedat.fu-berlin.de>
html2text-1.3.2a/configure 0100755 0000000 0000000 00000015131 10000540606 014207 0 ustar root root #! /bin/sh
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License in the file COPYING for more details.
# Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
# Dates and reasons of modifications:
# Son Mar 18 21:55:24 CET 2001
# Fre Jun 8 18:46:58 CEST 2001
# Thu Oct 4 21:54:50 CEST 2001
# Sun Apr 7 12:04:48 CEST 2002
# Tue Nov 11 21:30:26 CET 2003
echo='/bin/echo -e'
rm -rf configure-tmp || exit 1;
mkdir configure-tmp || exit 1;
tmp_file="configure-tmp/xxx";
makedirs=".";
#
# $CXX
#
$echo 'Checking C++ compiler... \c';
cat <<EOF >$tmp_file.C;
#include <iostream>
int main(int, char **) {
std::cout << "hello" << std::endl;
return 0;
}
EOF
CXX=unknown;
for i in "CC" "g++" "cc" "$CC"; do
if $i -c $tmp_file.C 2>/dev/null; then
CXX="$i";
break;
fi;
done;
if test "$CXX" = unknown; then
$echo "Error: Could not find a working C++ compiler.";
exit 1;
fi;
$echo "use \"$CXX\"";
#
# $SYS_POLL_MISSING
#
$echo 'Checking <sys/poll.h>... \c';
SYS_POLL_MISSING=unknown;
cat <<EOF >$tmp_file.C;
#ifdef SYS_POLL_MISSING /* { */
struct pollfd { int fd; short events; short revents; };
extern "C" int poll(struct pollfd *ufds, unsigned int nfds, int timeout);
#define POLLIN 0x0001
#define POLLPRI 0x0002
#define POLLOUT 0x0004
#define POLLERR 0x0008
#define POLLHUP 0x0010
#define POLLNVAL 0x0020
#else /* } { */
#include <sys/poll.h>
#endif /* } */
int main() {
struct pollfd fds[3];
return poll(fds, 3, 700);
}
EOF
for i in "" -DSYS_POLL_MISSING; do
if $CXX $tmp_file.C $i -o $tmp_file 2>/dev/null; then
SYS_POLL_MISSING="$i";
break;
fi;
done;
case "$SYS_POLL_MISSING" in
unknown)
$echo 'Error: Could not get "poll()" to working.';
exit 1;;
"")
$echo "OK";;
*)
$echo "use \"$SYS_POLL_MISSING\"";;
esac;
#
# $SOCKET_LIBRARIES
#
$echo 'Checking for socket libraries... \c';
SOCKET_LIBRARIES=unknown;
cat >$tmp_file.C <<EOF;
extern "C" int socket();
extern "C" void gethostbyname();
int main() {
socket();
gethostbyname();
return 0;
}
EOF
for i in "" "-lbsocket" "-lbsocket -lnsl" "-lsocket" "-lsocket -lnsl"; do
if $CXX $tmp_file.C $i -o $tmp_file 2>/dev/null; then
SOCKET_LIBRARIES="$i";
break;
fi;
done;
if test "$SOCKET_LIBRARIES" = unknown; then
$echo "Error: Could not determine the library for the socket API.";
exit 1;
fi;
if test "$SOCKET_LIBRARIES" = ""; then
$echo "no extra libraries required";
else
$echo "use \"$SOCKET_LIBRARIES\"";
fi;
#
# $BOOL_DEFINITION
#
$echo 'Checking "bool"... \c';
BOOL_DEFINITION=unknown;
cat <<EOF >$tmp_file.C;
#ifdef BOOL_DEFINITION
BOOL_DEFINITION
#endif
int main(int argc, char **) {
bool x = argc == 3;
x = !x;
if (x && argc == 7) x = false;
return 0;
}
EOF
for i in \
'' \
'-DBOOL_DEFINITION="typedef unsigned char bool;const bool false=0,true=1;"' \
'-DBOOL_DEFINITION="enum bool{false,true};"'; \
do
if eval "$CXX $tmp_file.C $i -o $tmp_file 2>/dev/null"; then
BOOL_DEFINITION="$i";
break;
fi;
done;
case "$BOOL_DEFINITION" in
unknown)
$echo 'Error: Could not a suitable definition for "bool".';
exit 1;;
"")
$echo "built-in";;
*)
$echo "use '$BOOL_DEFINITION'";;
esac;
#
# $EXPLICIT
#
$echo 'Checking "explicit"... \c';
EXPLICIT=unknown;
cat <<EOF >$tmp_file.C;
struct C {
explicit C(int) {}
};
int main(int, char **) { C x(7); return 0; }
EOF
for i in \
'' \
'-Dexplicit='; \
do
if eval "$CXX $tmp_file.C $i -o $tmp_file 2>/dev/null"; then
EXPLICIT="$i";
break;
fi;
done;
case "$EXPLICIT" in
unknown)
$echo 'Error: Could not a suitable definition for "explicit".';
exit 1;;
"")
$echo "built-in";;
*)
$echo "use '$EXPLICIT'";;
esac;
#
# $LIBSTDCXX_INCLUDES, $LIBSTDCXX_LIBS
#
$echo 'Checking Standard C++ library... \c';
cat <<EOF >$tmp_file.C;
#include <string>
#include <list>
#include <memory>
#include <utility>
#include <map>
#include <set>
#include <new>
#include <vector>
using namespace std;
void func() { map<string, string> x; }
EOF
if $CXX -c $tmp_file.C 2>/dev/null; then
LIBSTDCXX_INCLUDES="";
LIBSTDCXX_LIBS="";
$echo 'works; no need to make "./libstd"';
else
LIBSTDCXX_INCLUDES='-Ilibstd/include';
LIBSTDCXX_LIBS='libstd/libstd.a';
echo 'not available or not working; use "./libstd"';
makedirs="$makedirs ./libstd";
fi;
#
# $AUTO_PTR_BROKEN
#
AUTO_PTR_BROKEN="";
$echo 'Checking "auto_ptr"... \c';
cat <<EOF >$tmp_file.C;
#include <memory>
#include <string>
#include <list>
using namespace std;
int main(int, char**) {
auto_ptr<string> x(new string("hello"));
*x = "world";
(void) x.get();
(void) x.release();
x.reset(0); // egcs-2.91.66 lacks "reset()"!
// G++ 2.95.1 on AIX 4.2 cannot compile this:
auto_ptr<int> api;
list<auto_ptr<int> > lapi;
lapi.push_back(api);
return 0;
}
EOF
if eval "$CXX -c $LIBSTDCXX_INCLUDES $EXPLICIT $BOOL_DEFINITION $tmp_file.C" 2>/dev/null; then
$echo 'defined in <memory>, good';
else
$echo 'not defined or not working, use "./libstd/include/auto_ptr.h"';
AUTO_PTR_BROKEN="-DAUTO_PTR_BROKEN";
fi;
#
# $MAKEDEPEND_INCLUDES
#
MAKEDEPEND_INCLUDES="";
$echo 'Checking "makedepend" includes... \c';
echo "#include <iostream>" >$tmp_file.C;
MAKEDEPEND_INCLUDES=`$CXX -E $tmp_file.C 2>/dev/null |
sed -n \
-e 's/^#line .*"\(\/.*\)\/.*".*/-I\1/p' \
-e 's/^# [1-9][0-9]* "\(\/.*\)\/.*".*/-I\1/p' |
sort -u |
tr '\n' ' '`;
if test "$MAKEDEPEND_INCLUDES" = ""; then
$echo none;
else
$echo "use \"$MAKEDEPEND_INCLUDES\"";
fi;
#
# Create "Makefile" from "Makefile.in".
#
rm -f Makefile libstd/Makefile;
cmd=sed;
for i in \
SYS_POLL_MISSING \
SOCKET_LIBRARIES \
CXX \
BOOL_DEFINITION \
EXPLICIT \
LIBSTDCXX_INCLUDES \
LIBSTDCXX_LIBS \
AUTO_PTR_BROKEN \
MAKEDEPEND_INCLUDES; \
do cmd="$cmd -e \"s|@$i@|\$$i|g\""; done;
for dir in $makedirs; do
$echo "Creating \"$dir/Makefile\" from \"$dir/Makefile.in\"... \\c";
cat <<EOF >$dir/Makefile;
#
# This make file was generated from "Makefile.in" by "./configure" on
# `date` -- all your changes will be lost if you
# run "./configure" again!
#
EOF
eval "$cmd" <$dir/Makefile.in >>$dir/Makefile;
$echo 'done';
if test -f $dir/Dependencies; then true; else >$dir/Dependencies; fi;
done;
#
# Clean up.
#
rm -rf configure-tmp;
rm -f xxx.o;
cat <<EOF;
Preparing completed. You may now run "make" (or "gmake").
EOF
html2text-1.3.2a/Properties.C 0100644 0000000 0000000 00000010100 07760112171 014542 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Fre Jun 8 17:24:35 CEST 2001: new method
* Wed Jul 2 22:02:51 CEST 2003: ported to g++ 3.3
*/
/***************************************************************************/
#include <ctype.h>
#include <iostream>
#include "Properties.h"
/* ------------------------------------------------------------------------- */
const char *
Properties::getProperty(const char *key, const char *dflt) const
{
map<string, string>::const_iterator i;
i = property_map.find(key);
return i == property_map.end() ? dflt : (*i).second.c_str();
}
// neue Methode fuer leere Attribute - Johannes Geiger
const char *
Properties::getProperty(const char *key) const
{
map<string, string>::const_iterator i;
i = property_map.find(key);
return i == property_map.end() ? NULL : (*i).second.c_str();
}
/* ------------------------------------------------------------------------- */
void
Properties::load(istream &is)
{
string key, value;
while (readProperty(is, &key, &value)) setProperty(key, value);
}
/* ------------------------------------------------------------------------- */
/*
* Expand the escape sequence at "line[pos]". Backslash-Newline reads another
* line from "is".
*/
static void
expandEscape(string *line_in_out, string::size_type *pos_in_out, istream &is)
{
for (;;) {
if (line_in_out->at(*pos_in_out) != '\\') { ++*pos_in_out; return; }
if (*pos_in_out != line_in_out->size() - 1) break;
string tmp;
if (!getline(is, tmp)) {++*pos_in_out; return; }
int j;
for (j = 0; j < tmp.size() && isspace(tmp[j]); ++j);
line_in_out->replace(
*pos_in_out, string::npos,
tmp, j, string::npos
);
}
char c = line_in_out->at(*pos_in_out + 1);
switch (c) {
case 't': c = '\t'; break;
case 'n': c = '\n'; break;
case 'r': c = '\r'; break;
}
line_in_out->replace(*pos_in_out, 2, &c, 1);
++*pos_in_out;
}
/*static*/ bool
Properties::readProperty(istream &is, string *key_return, string *value_return)
{
string line;
string::size_type i, l;
// Skip empty and comment lines.
for (;;) {
if (!getline(is, line)) return false;
l = line.size();
// Skip leading white-space.
for (i = 0; i < l && isspace(line[i]); ++i);
if (i == l) continue; // Line contains only white-space.
// Ignore comment lines.
if (line[i] == '#' || line[i] == '!') continue; // Comment line.
break;
}
// Parse key.
string::size_type bok = i;
while (i < line.size()) {
char c = line[i];
if (isspace(c) || c == '=' || c == ':') break;
expandEscape(&line, &i, is);
}
string::size_type eok = i;
// Skip key terminator.
while (i < l && isspace(line[i])) ++i;
if (i < l && (line[i] == '=' || line[i] == ':')) {
for (++i; i < l && isspace(line[i]); ++i);
}
// Substitute escape sequences in value.
string::size_type bov = i;
while (i < line.size()) expandEscape(&line, &i, is);
// Return key and value.
key_return->assign(line, bok, eok - bok);
value_return->assign(line, bov, string::npos);
return true;
}
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/Properties.h 0100644 0000000 0000000 00000005302 07760112171 014617 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Fre Jun 8 17:29:50 CEST 2001
* Thu Oct 4 22:38:59 CEST 2001: ported to g++ 3.0
* Wed Jul 2 22:03:29 CEST 2003: ported to g++ 3.3
*/
/***************************************************************************/
#ifndef __Properties_h_INCLUDED__ /* { */
#define __Properties_h_INCLUDED__
/* ------------------------------------------------------------------------- */
#ifdef BOOL_DEFINITION
BOOL_DEFINITION
#undef BOOL_DEFINITION
#endif
#include <string>
#include <map>
#include <istream>
using std::string;
using std::map;
using std::istream;
/* ------------------------------------------------------------------------- */
class Properties {
public:
const char *getProperty(const char *key, const char *dflt) const;
const char *getProperty(const char *key) const;
void setProperty(const string &key, const string &value)
{ property_map[key] = value; }
void setProperty(const char *key, const string &value)
{ property_map[key] = value; }
void setProperty(const string &key, const char *value)
{ property_map[key] = value; }
void setProperty(const char *key, const char *value)
{ property_map[key] = value; }
// Read from file.
void load(istream &);
private:
static bool readProperty(
istream &is,
string *key_return,
string *value_return
);
map<string, string> property_map;
};
/* ------------------------------------------------------------------------- */
#endif /* } */
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/README 0100644 0000000 0000000 00000020020 10001242725 013153 0 ustar root root ## This is the README file for html2text Wed Jan 14 14:35:57 CET 2004
## ===========================================================================
html2text is a command line utility, written in C++, that converts HTML
documents into plain text. It was written up to version 1.2.2 for and is
copyrighted by GMRS Software GmbH, Unterschleißheim.
html2text reads HTML documents from standard input or a (local or remote)
URI, and formats them into a stream of plain text characters that is written
to standard output or into an output-file, preserving the original positions
of table fields.
ISO 8859-1 is used for output by default, plain-ASCII output can be chosen by
setting the "-ascii" command line option. Type "html2text -help" for an
overview of all command line options.
Examples:
html2text <file> | less
html2text -o outfile.txt -ascii -nobs <file>
The rendering is largely customisable through the "html2textrc" file and the
"-style" command line option, that may be used to change quickly some
formatting defaults. See the html2textrc(5) manual page for details.
Although html2text was written for the conversion of HTML 3.2 documents, most
constructs of HTML 4 are renderred as well, including most SGML entities,
provided that they are written as "named entities" and not as a numeric value.
The program tries to parse even XHTML documents and the HTML produced by word
processors, but this not always as successful as other HTML parsers, because
html2text is, as already said, for all that an HTML 3.2 converter.
The program accepts also syntactically incorrect input, attempting to
interpret it "reasonably". If the output is however not satisfactory, of if
rendering fails completely, and you have the possibility to correct the HTML
source code, you may want to use the "-unparse" or "-check" options to find
out what exactly html2text's problem is.
This program was written because GMRS was looking for a good, free
HTML-to-text converter for UNIX, and they couldn't find one on the net. The
best they could find was lynx, i.e. "lynx -dump", but lynx could not cope with
tables.
# ----------------------------------------------------------------------------
# For information on compiling and installing the package on your system,
# please refer to the file INSTALL.
html2text was developed and is tested under Linux. However, it uses no
O/S-specific features and should be easily portable to other platforms (at
least to other UNIX-ish platforms). It is reported to compile and work on the
following platforms:
+ AIX 4.3/g++ 2.95.1
+ AIX 4.3.2.0/g++ 2.95.2.1
+ CYGWIN_NT-5.0 1.5.4/gcc 3.2
+ FreeBSD 5.1/gcc 3.2.1
+ IRIX64 6.5/MIPS 7.41
+ Linux 2.2.18/g++ 2.95.2
+ Linux 2.4.16/g++ 2.95.3
+ Linux 2.4.22/gcc 3.3.2
+ NetBSD 1.6.1/gcc 2.95
+ SINIX/CDS++ 2.0A00
You will find some hints for porting it to other platforms at the end of the
file "INSTALL".
Note for version 1.3.2(a): Version 1.3.2 is distributed in two "flavours":
1.3.2A contains changes needed for g++ 3.3 and later, which are not
backwards-compatible. Thus, if you use an older (or other) compiler, please
use version 1.3.2 (without 'a'), if you have g++ 3.3 (and up) installed,
please use version 1.3.2A. Cross-patches (from 1.3.2 to 1.3.2a and viceversa)
are included into the source code packages of either flavours.
# ----------------------------------------------------------------------------
# Published under the terms of the GNU General Public License.
This program is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free Software
Foundation; either version 2 of the License, or (at your option) any later
version.
This program is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
You should have received a copy of the GNU General Public License along with
this program; if not, write to the Free Software Foundation, Inc., 59 Temple
Place - Suite 330, Boston, MA 02111-1307, USA.
# ----------------------------------------------------------------------------
# GMRS agreed to change the program's license terms to GPL.
Message-ID: <01c401c10f72$d11c3660$12c8a8c0@jag>
Reply-To: "David Geffen" <geffen@one4net.com>
From: "David Geffen" <david@one4net.com>
To: <mbayer@zedat.fu-berlin.de>
Date: Wed, 18 Jul 2001 12:17:14 +0200
Organization: GMRS Software GmbH
Hallo Herr Bayer,
html2text darf unter die GPL veroeffentlicht werden, solange one4net keinerlei
Nachteile oder Verpflichtungen dadurch entstehen.
Mit freundlichen Gruessen
David Geffen
----- Original Message -----
From: "Martin Bayer" <mbayer@zedat.fu-berlin.de>
To: <geffen@one4net.com>
Sent: Thursday, July 12, 2001 5:39 PM
Subject: Re: Lizenzbedingungen von 'html2text'
> Guten Tag!
>
> On Mon, Jun 25, 2001 at 03:23:31PM +0200, David Geffen wrote:
> > > Aus diesem Grunde möchte ich Sie herzlich bitten, zu überlegen, ob es
> > > für GMRS nicht möglich wäre, 'html2text' nachträglich unter die GPL zu
> > > stellen.
> >
> > ich bin erst heute zurueck aus dem Urlaub gekommen.
> >
> > Ich werde mich in den naechsten paar Tage dazu melden.
>
> Darf ich Sie fragen, ob Sie in dieser Angelegenheit bereits zu einem
> Entschluss gekommen sind? Es ist mittlerweile gelungen, das Programm nach
> g++3 zu portieren, und da wäre es schön, wenn bereits diese neue Version
> unter GPL veröffentlicht werden könne.
>
> Mit den besten Grüßen
> --
> Martin Bayer
> c.ne Ostiense, 212/E/15
> E-Mail: mail@mbayer.de I-00154 Roma
> WWW: http://www.mbayer.de GSM: +39 3476605285
# ----------------------------------------------------------------------------
# This program is not provided nor supported by GMRS any longer.
Since GMRS decided not to develop nor to support this program any longer,
they also did not provide its source code any more. With this, I realised,
the source code of this program was hardly to obtain, as most archives
included at best a precompiled version. Because I liked the features, I
offered a webspace where this program now is living at,
http://userpage.fu-berlin.de/~mbayer/tools/html2text.html
I'm afraid in this way I've become the maintainer of this package, even if I
actually don't have time free to spend on working on the program by myself.
Please keep this in mind if you are going to write me. :-)
The source code can also be obtained from the Ibiblio network at
[ftp|http]://ftp.ibiblio.org/pub/linux/apps/www/converters/
If you are going to retrieve the source code from within automated scripts,
e.g. by a software packaging manager, please prefer downloading it from the
Ibiblio server or one of its mirrors.
# ----------------------------------------------------------------------------
# »We accept patches.«
Please include in all your messages information on
· the version of html2text you are referring to (`html2text -version`),
if you obtained the program in binary form, the version number as
supplied by your package manager (e.g. `rpm -q html2text`);
· name and version of your operating system (`uname -a`);
· name and version of your compiler (`cc -v`).
If you think you found a possible security impact, please let _me_ know
_first_.
If you think you found a bug, please try first to find out its possible
reason by yourself, using the "-unparse", "-check", "-debug-scanner", and
"-debug-parser" command line options, in order to save other people's time. I
will not consider any "bug report" that just claims "your program is
buggy!!!!!1", nor will I answer to any mail asking me O/S-specific questions.
I will include into the TODO list any sensible feature request.
And, last but not least, patches are always very welcome. :-)
Martin Bayer <mbayer@zedat.fu-berlin.de>
For all e-mails, use of PGP (GPG) is encouraged. You will find my
public key (ID: 0xCB537B60) on my homepage and on keyservers. The key's
fingerprint is: "46A1 B556 41CD C77A 0261 D22F 41A6 EB90 CB53 7B60".
html2text-1.3.2a/auto_aptr.h 0100644 0000000 0000000 00000006273 07357140447 014502 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*
* All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* "This product includes software developed by GMRS Software GmbH."
* The name of GMRS Software GmbH may not be used to endorse or promote
* products derived from this software without specific prior written
* permission.
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Thu Oct 4 21:29:40 CEST 2001: ported to g++ 3.0
*/
/***************************************************************************/
#ifndef __auto_aptr_h_INCLUDED__ /* { */
#define __auto_aptr_h_INCLUDED__
/* ------------------------------------------------------------------------- */
#ident "$Id: auto_aptr.h,v 1.2 1999/07/09 09:08:40 arno Exp $"
/* ------------------------------------------------------------------------- */
/*
* This template class is very similar to the standard "auto_ptr", but it is
* used for *array* pointers rather than *object* pointers, i.e. the pointer
* passed to it must have been allocated with "new[]", and "auto_aptr" will
* delete it with "delete[]".
*/
/* ------------------------------------------------------------------------- */
#include <stdlib.h>
template <class T>
class auto_aptr {
public:
// Constructor/copy/destroy
auto_aptr() : p(0) {}
auto_aptr(T *x) : p(x) {}
auto_aptr(const auto_aptr<T> &x) : p(x.p) { ((auto_aptr<T> *) &x)->p = 0; }
void operator=(const auto_aptr<T> &x)
{ delete[] p; p = x.p; ((auto_aptr<T> *) &x)->p = 0; }
// Extension: "operator=(T *)" is identical to "auto_aptr::reset(T *)".
void operator=(T *x) { delete[] p; p = x; }
~auto_aptr() { delete[] p; }
// Members
T &operator[](size_t idx) const { if (!p) abort(); return p[idx]; }
T *get() const { return (T *) p; }
T *release() { T *tmp = p; p = 0; return tmp; }
void reset(T *x = 0) { delete[] p; p = x; }
// These would make a nice extension, but are not provided by many other
// implementations.
//operator const void *() const { return p; }
//int operator!() const { return p == 0; }
private:
T *p;
};
/* ------------------------------------------------------------------------- */
#endif /* } */
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/cmp_nocase.C 0100644 0000000 0000000 00000005067 06771645270 014551 0 ustar root root
/* ------------------------------------------------------------------------- */
/*
* Copyright (c) 1999
* GMRS Software GmbH, Innsbrucker Ring 159, 81669 Munich, Germany.
* http://www.gmrs.de
* All rights reserved.
* Author: Arno Unkrig (arno.unkrig@gmrs.de)
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by GMRS Software GmbH.
* 4. The name of GMRS Software GmbH may not be used to endorse or promote
* products derived from this software without specific prior written
* permission.
*
* THIS SOFTWARE IS PROVIDED BY GMRS SOFTWARE GMBH ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL GMRS SOFTWARE GMBH BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
* THE POSSIBILITY OF SUCH DAMAGE.
*/
/* ------------------------------------------------------------------------- */
#ident "$Id: cmp_nocase.C,v 1.1 1999/09/21 09:07:04 arno Exp $"
#include <ctype.h>
#include "cmp_nocase.h"
/* ------------------------------------------------------------------------- */
int
_cmp_nocase(const char *s1, size_t l1, const char *s2, size_t l2)
{
const char *e1 = s1 + l1;
const char *e2 = s2 + l2;
while (s1 != e1 && s2 != e2) {
int c1 = toupper(*s1);
int c2 = toupper(*s2);
if (c1 < c2) return -1;
if (c1 > c2) return 1;
++s1, ++s2;
}
return s1 != e1 ? 1 : s2 != e2 ? -1 : 0;
}
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/cmp_nocase.h 0100644 0000000 0000000 00000005367 07357142174 014615 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*
* All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* "This product includes software developed by GMRS Software GmbH."
* The name of GMRS Software GmbH may not be used to endorse or promote
* products derived from this software without specific prior written
* permission.
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Thu Oct 4 21:31:58 CEST 2001: ported to g++ 3.0
*/
/***************************************************************************/
#ifndef __cmp_nocase_h_INCLUDED__ /* { */
#define __cmp_nocase_h_INCLUDED__
/* ------------------------------------------------------------------------- */
#include <string.h>
#include <string>
using std::string;
/* ------------------------------------------------------------------------- */
/*
* The Standard C++ library is lacking a case-insensitive string comparison
* function... so I define my own, adapting Stroustrup's ("The C++ Programming
* Language", 3rd edition).
*/
// Helper
extern int _cmp_nocase(const char *s1, size_t l1, const char *s2, size_t l2);
// -1: s1 < s2; 0: s1 == s2, 1: s1 > s2
inline int cmp_nocase(const string &s1, const string &s2)
{ return _cmp_nocase(s1.data(), s1.length(), s2.data(), s2.length()); }
inline int cmp_nocase(const char *s1, const string &s2)
{ return _cmp_nocase(s1, strlen(s1), s2.data(), s2.length()); }
inline int cmp_nocase(const string &s1, const char *s2)
{ return _cmp_nocase(s1.data(), s1.length(), s2, strlen(s2)); }
inline int cmp_nocase(const char *s1, const char *s2)
{ return _cmp_nocase(s1, strlen(s1), s2, strlen(s2)); }
/* ------------------------------------------------------------------------- */
#endif /* } */
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/Makefile.in 0100644 0000000 0000000 00000010311 10001244126 014337 0 ustar root root
# -----------------------------------------------------------------------------
#
# Portions Copyright (c) 1999 GMRS Software GmbH
# Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
# All rights reserved.
#
# Author: Arno Unkrig <arno@unkrig.de>
#
# This program is free software; you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free Software
# Foundation; either version 2 of the License, or (at your option) any later
# version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE. See the GNU General Public License in the file
# COPYING for more details.
#
# -----------------------------------------------------------------------------
#
# Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
#
# -----------------------------------------------------------------------------
VERSION=1.3.2a
BISONXX = bison++
YFLAGS =
INSTALLER = install
BINDIR = /usr/local/bin
MANDIR = /usr/local/man
DOCDIR = /usr/share/doc/html2text
CXX = @CXX@
BOOL_DEFINITION = @BOOL_DEFINITION@
EXPLICIT = @EXPLICIT@
SYS_POLL_MISSING = @SYS_POLL_MISSING@
SOCKET_LIBRARIES = @SOCKET_LIBRARIES@
LIBSTDCXX_INCLUDES = @LIBSTDCXX_INCLUDES@
LIBSTDCXX_LIBS = @LIBSTDCXX_LIBS@
AUTO_PTR_BROKEN = @AUTO_PTR_BROKEN@
MAKEDEPEND_INCLUDES = @MAKEDEPEND_INCLUDES@
DEBUG=-O2 -g
INCLUDES = $(LIBSTDCXX_INCLUDES)
DEFINES = -DVERSION=$(VERSION) $(SYS_POLL_MISSING) $(BOOL_DEFINITION) $(EXPLICIT) $(AUTO_PTR_BROKEN)
CPPFLAGS = $(INCLUDES) $(DEFINES)
CXXFLAGS = $(CPPFLAGS) $(DEBUG)
LDFLAGS = $(DEBUG)
LOADLIBES = $(LIBSTDCXX_LIBS) $(SOCKET_LIBRARIES)
.SUFFIXES : .C .o
.C.o :
$(CXX) -c $(CXXFLAGS) $*.C
# -----------------------------------------------------------------------------
default : all
all : html2text
@echo ;
@echo 'Compilation completed. You may now move "html2text", "html2text.1.gz"';
@echo 'and "html2textrc.5.gz" to their installation directories (e.g.';
@echo '"/usr/local/bin", "/usr/local/man/man1" and "/usr/local/man/man5").';
@echo
OBJS = html2text.o html.o HTMLControl.o HTMLParser.o Area.o format.o sgml.o table.o urlistream.o Properties.o cmp_nocase.o
html2text : $(OBJS) $(LIBSTDCXX_LIBS)
$(CXX) $(LDFLAGS) $(OBJS) $(LOADLIBES) $(LDLIBS) -o $@
libstd/libstd.a :
cd libstd && $(MAKE)
# -----------------------------------------------------------------------------
# Since it is very unlikely that bison++-2.2 is installed (available on
# html2text's homepage), HTMLParser.h and HTMLParser.C are only built when
# 'make bison-local' is issued.
bison-local :
cmp -s HTMLParser.h HTMLParser.k || cp HTMLParser.k HTMLParser.h;
$(BISONXX) $(YFLAGS) -o HTMLParser.C -d -h HTMLParser.k HTMLParser.y
# -----------------------------------------------------------------------------
# This is mostly thought for RPM builts and users that don't read the documentation.
install :
$(INSTALLER) -s -m 755 html2text $(BINDIR);
$(INSTALLER) -m 644 html2text.1.gz $(MANDIR)/man1;
$(INSTALLER) -m 644 html2textrc.5.gz $(MANDIR)/man5;
$(INSTALLER) -d -m 755 $(DOCDIR);
$(INSTALLER) -p -m 644 CHANGES COPYING CREDITS KNOWN_BUGS README RELEASE_NOTES TODO $(DOCDIR)
# -----------------------------------------------------------------------------
SUBDIRS = libstd
# "./configure" creates "Makefile"s only in the subdirectories that need to
# be built, so we check for the existance of these "Makefile".
clean clobber depend :
@for i in $(SUBDIRS); do \
if test -r $$i/Makefile; then \
( \
cd $$i && echo "*** make $@ in `pwd`" && $(MAKE) $@ || \
{ echo "*** make $@ error in `pwd`" && false; } \
) || exit 1; \
echo "*** Back in `pwd`"; \
fi; \
done;
clean : local-clean
local-clean :
rm -f *.o *~ core html2text;
clobber : local-clobber
local-clobber : local-clean
rm -f html2text
depend : local-depend
local-depend : HTMLParser.h
@>Dependencies
makedepend -f Dependencies $(CPPFLAGS) $(MAKEDEPEND_INCLUDES) *.C
@rm -f Dependencies.bak
# -----------------------------------------------------------------------------
include Dependencies
html2text-1.3.2a/format.C 0100644 0000000 0000000 00000126450 07760112171 013716 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Sun Mar 18 19:51:54 CET 2001: fixed segfault
* Fre Jun 8 17:37:12 CEST 2001: new image handling
* Thu Oct 4 21:34:26 CEST 2001: ported to g++ 3.0
* Mon Jul 29 13:09:26 CEST 2002: fixed runtime increment
* Wed Jul 2 22:04:08 CEST 2003: ported to g++ 3.3
*/
/***************************************************************************/
#include <sstream>
#include <stdlib.h>
#include <ctype.h>
#include <vector>
#include <map>
#include "html.h"
#include "HTMLParser.h"
#include "sgml.h"
#include "cmp_nocase.h"
#include "format.h"
#include "Properties.h"
using std::endl;
using std::flush;
#ifndef nelems
#define nelems(array) (sizeof(array) / sizeof((array)[0]))
#endif
/* ------------------------------------------------------------------------- */
static Line *line_format(const list<auto_ptr<Element> > *elements);
static Area *make_up(const Line &line, Area::size_type w, int halign);
static Area *format(
const list<auto_ptr<Element> > *elements,
Area::size_type w,
int halign
);
static void format(
const list<auto_ptr<Element> > *elements,
Area::size_type indent_left,
Area::size_type w,
int halign,
ostream &os
);
/* ------------------------------------------------------------------------- */
/*
* Helper class that retrieves several block-formatting properties in one
* go.
*/
struct BlockFormat {
Area::size_type vspace_before;
Area::size_type vspace_after;
Area::size_type indent_left;
Area::size_type indent_right;
BlockFormat(
const char *item_name,
Area::size_type default_vspace_before = 0,
Area::size_type default_vspace_after = 0,
Area::size_type default_indent_left = 0,
Area::size_type default_indent_right = 0
);
Area::size_type effective_width(Area::size_type) const;
};
/*
* Helper class that retrieves several list-formatting properties in one
* go.
*/
struct ListFormat {
Area::size_type vspace_before;
Area::size_type vspace_between;
Area::size_type vspace_after;
auto_ptr<vector<int> > indents;
auto_ptr<vector<string> > default_types;
ListFormat(
const char *item_name,
Area::size_type default_vspace_before = 0,
Area::size_type default_vspace_between = 0,
Area::size_type default_vspace_after = 0,
const char *default_indents = "6",
const char *default_default_types = "DISC CIRCLE SQUARE"
);
Area::size_type get_indent(int nesting) const;
const string &get_default_type(int nesting) const;
int get_type(
const list<TagAttribute> *attributes,
int nesting,
int default_default_type
) const;
};
/* ------------------------------------------------------------------------- */
// Attributes: VERSION (ignored)
Area *
Document::format(Area::size_type w, int halign) const
{
static BlockFormat bf("DOCUMENT");
auto_ptr<Area> res(body.format(bf.effective_width(w), halign));
if (!res.get()) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
void
Document::format(
Area::size_type indent_left,
Area::size_type w,
int halign,
ostream &os
) const
{
static BlockFormat bf("DOCUMENT");
for (int i = 0; i < bf.vspace_before; ++i) os << endl;
body.format(
indent_left + bf.indent_left, bf.effective_width(w), halign,
os
);
for (int j = 0; j < bf.vspace_after; ++j) os << endl;
}
/* ------------------------------------------------------------------------- */
// Attributes: BACKGROUND BGCOLOR TEXT LINK VLINK ALINK (ignored)
Area *
Body::format(Area::size_type w, int halign) const
{
static BlockFormat bf("BODY");
auto_ptr<Area> res(
::format(content.get(), bf.effective_width(w), halign)
);
if (!res.get()) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
void
Body::format(
Area::size_type indent_left,
Area::size_type w,
int halign,
ostream &os
) const
{
static BlockFormat bf("BODY");
for (int i = 0; i < bf.vspace_before; ++i) os << endl;
::format(
content.get(),
indent_left + bf.indent_left, bf.effective_width(w), halign,
os
);
for (int j = 0; j < bf.vspace_after; ++j) os << endl;
}
/* ------------------------------------------------------------------------- */
enum {
NO_BULLET,
ARABIC_NUMBERS, LOWER_ALPHA, UPPER_ALPHA, LOWER_ROMAN, UPPER_ROMAN,
DISC, SQUARE, CIRCLE, CUSTOM1, CUSTOM2, CUSTOM3
};
// Attributes: TYPE (processed) COMPACT (ignored)
Area *
OrderedList::format(Area::size_type w, int /*halign*/ ) const
{
if (!items.get()) return 0;
static ListFormat lf("OL", 0, 0, 0, "6", "1");
int type = lf.get_type(attributes.get(), nesting, ARABIC_NUMBERS);
auto_ptr<Area> res;
const list<auto_ptr<ListItem> > &il(*items);
list<auto_ptr<ListItem> >::const_iterator i;
int number = 1;
for (i = il.begin(); i != il.end(); ++i) {
auto_ptr<Area> a((*i)->format(w, type, lf.get_indent(nesting), &number));
if (a.get()) {
if (res.get()) {
res->append(lf.vspace_between);
} else {
res.reset(new Area);
res->append(lf.vspace_before);
}
*res += *a;
}
}
if (res.get()) res->append(lf.vspace_after);
return res.release();
}
/*
* <UL>, <DIR> and <MENU> are currently formatted totally identically, because
* this is what Netscape does, and the HTML 3.2 spec and "HTML -- The
* Definitive Guide" give no clear indication as to how to format them.
*/
// Attributes: TYPE (processed) COMPACT (ignored)
Area *
UnorderedList::format(Area::size_type w, int /*halign*/ ) const
{
if (!items.get()) return 0;
static ListFormat lf("UL");
int type = lf.get_type(attributes.get(), nesting, SQUARE);
auto_ptr<Area> res;
const list<auto_ptr<ListItem> > &il(*items);
list<auto_ptr<ListItem> >::const_iterator i;
for (i = il.begin(); i != il.end(); ++i) {
auto_ptr<Area> a((*i)->format(w, type, lf.get_indent(nesting)));
if (a.get()) {
if (res.get()) {
res->append(lf.vspace_between);
} else {
res.reset(new Area);
res->append(lf.vspace_before);
}
*res += *a;
}
}
if (res.get()) res->append(lf.vspace_after);
return res.release();
}
// Attributes: TYPE (extension, processed) COMPACT (ignored)
Area *
Dir::format(Area::size_type w, int /*halign*/ ) const
{
if (!items.get()) return 0;
static ListFormat lf("DIR");
int type = lf.get_type(attributes.get(), nesting, SQUARE);
auto_ptr<Area> res;
const list<auto_ptr<ListItem> > &il(*items);
list<auto_ptr<ListItem> >::const_iterator i;
for (i = il.begin(); i != il.end(); ++i) {
auto_ptr<Area> a((*i)->format(w, type, lf.get_indent(nesting)));
if (a.get()) {
if (res.get()) {
res->append(lf.vspace_between);
} else {
res.reset(new Area);
res->append(lf.vspace_before);
}
*res += *a;
}
}
if (res.get()) res->append(lf.vspace_after);
return res.release();
}
// Attributes: TYPE (extension, processed) COMPACT (ignored)
Area *
Menu::format(Area::size_type w, int /*halign*/ ) const
{
if (!items.get()) return 0;
static ListFormat lf("MENU", 0, 0, 0, "2", "NO_BULLET");
int type = lf.get_type(attributes.get(), nesting, NO_BULLET);
auto_ptr<Area> res;
const list<auto_ptr<ListItem> > &il(*items);
list<auto_ptr<ListItem> >::const_iterator i;
for (i = il.begin(); i != il.end(); ++i) {
auto_ptr<Area> a((*i)->format(w, type, lf.get_indent(nesting)));
if (a.get()) {
if (res.get()) {
res->append(lf.vspace_between);
} else {
res.reset(new Area);
res->append(lf.vspace_before);
}
*res += *a;
}
}
if (res.get()) res->append(lf.vspace_after);
return res.release();
}
// Attributes: TYPE VALUE (ignored)
Area *
ListNormalItem::format(
Area::size_type w,
int type,
Area::size_type indent,
int *number_in_out /*= 0*/
) const
{
int number = 0;
if (number_in_out) {
number = *number_in_out = get_attribute(
attributes.get(), "VALUE", *number_in_out
);
}
static const char *disc_bullet =
Formatting::getString("LI.disc_bullet", "*");
static const char *square_bullet =
Formatting::getString("LI.square_bullet", "#");
static const char *circle_bullet =
Formatting::getString("LI.circle_bullet", "o");
static const char *custom1_bullet =
Formatting::getString("LI.custom1_bullet", "+");
static const char *custom2_bullet =
Formatting::getString("LI.custom2_bullet", "-");
static const char *custom3_bullet =
Formatting::getString("LI.custom3_bullet", "~");
string bullet;
switch (type) {
case NO_BULLET: break;
case DISC: bullet = disc_bullet; break;
case SQUARE: bullet = square_bullet; break;
case CIRCLE: bullet = circle_bullet; break;
case CUSTOM1: bullet = custom1_bullet; break;
case CUSTOM2: bullet = custom2_bullet; break;
case CUSTOM3: bullet = custom3_bullet; break;
case ARABIC_NUMBERS:
{
std::ostringstream oss;
oss << number << '.'; // << std::ends;
bullet = oss.str();
// oss.rdbuf()->freeze(0);
}
break;
case LOWER_ALPHA:
bullet = number <= 26 ? (char) (number - 1 + 'a') : 'z';
bullet += '.';
break;
case UPPER_ALPHA:
bullet = number <= 26 ? (char) (number - 1 + 'A') : 'Z';
bullet += '.';
break;
case LOWER_ROMAN:
{
static const char *lower_roman[] = {
"0", "i", "ii", "iii", "iv", "v", "vi", "vii", "viii", "ix",
"x", "xi", "xii", "xiii", "xiv", "xv", "xvi", "xvii", "xviii", "xix",
"xx","xxi","xxii","xxiii","xxiv","xxv","xxvi","xxvii","xxviii","xxix"
};
const char *p = (
number >= 0 && number < (int) nelems(lower_roman) ?
lower_roman[number] :
"???"
);
bullet = p;
bullet += '.';
}
break;
case UPPER_ROMAN:
{
static const char *upper_roman[] = {
"0", "I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX",
"X", "XI", "XII", "XIII", "XIV", "XV", "XVI", "XVII", "XVIII", "XIX",
"XX","XXI","XXII","XXIII","XXIV","XXV","XXVI","XXVII","XXVIII","XXIX"
};
const char *p = (
number >= 0 && number < (int) nelems(upper_roman) ?
upper_roman[number] :
"???"
);
bullet = p;
bullet += '.';
}
break;
}
if (bullet.length() >= indent) indent = bullet.length() + 1;
auto_ptr<Area> res(::format(flow.get(), w - indent, Area::LEFT));
// KLUDGE: Some people write "<UL> <B><LI>Bla</B>Bla </UL>", which actually
// defines a bold and empty list item before "Bla Bla". This is very
// difficult to handle... so... let's just ignore empty list items.
if (!res.get()) return 0;
*res >>= indent;
res->insert(bullet, indent - bullet.length() - 1, 0);
if (number_in_out) (*number_in_out)++;
return res.release();
}
Area *
ListBlockItem::format(
Area::size_type w,
int /*type*/,
Area::size_type indent,
int * /*number_in_out*/ /*= 0*/
) const
{
if (!block.get()) return 0;
auto_ptr<Area> res(block->format(w - indent, Area::LEFT));
if (!res.get()) return 0;
/*
* Hm... shouldn't there be a bullet before the item?
*/
*res >>= indent;
return res.release();
}
/* ------------------------------------------------------------------------- */
// Attributes: COMPACT (ignored)
Area *
DefinitionList::format(Area::size_type w, int halign) const
{
static struct DefinitionListFormat {
const Area::size_type vspace_before;
const Area::size_type vspace_between;
const Area::size_type vspace_after;
DefinitionListFormat() :
vspace_before (Formatting::getInt("DL.vspace.before", 0)),
vspace_between(Formatting::getInt("DL.vspace.between", 0)),
vspace_after (Formatting::getInt("DL.vspace.after", 0))
{}
} dlf;
auto_ptr<Area> res;
if (preamble.get()) {
res.reset(::format(preamble.get(), w, halign));
if (res.get()) res->prepend(dlf.vspace_before);
}
if (items.get()) {
const list<auto_ptr<DefinitionListItem> > &il(*items);
list<auto_ptr<DefinitionListItem> >::const_iterator i;
for (i = il.begin(); i != il.end(); ++i) {
auto_ptr<Area> a((*i)->format(w, halign));
if (!a.get()) continue;
if (res.get()) {
res->append(dlf.vspace_between);
*res += *a;
} else {
res = a;
res->prepend(dlf.vspace_before);
}
}
}
if (res.get()) res->append(dlf.vspace_after);
return res.release();
}
Area *
TermName::format(Area::size_type w, int halign) const
{
static BlockFormat bf("DT", 0, 0, 2);
auto_ptr<Area> res(::format(flow.get(), bf.effective_width(w), halign));
if (!res.get()) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
Area *
TermDefinition::format(Area::size_type w, int halign) const
{
static BlockFormat bf("DD", 0, 0, 6);
auto_ptr<Area> res(::format(flow.get(), bf.effective_width(w), halign));
if (!res.get()) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
/* ------------------------------------------------------------------------- */
// Attributes: ALIGN NOSHADE SIZE WIDTH (ignored)
Area *
HorizontalRule::format(Area::size_type w, int /*halign*/ ) const
{
static const char *marker = Formatting::getString("HR.marker", "=");
static BlockFormat bf("HR");
Area *res = new Area(bf.effective_width(w), 1, *marker ? *marker : ' ');
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res;
}
/* ------------------------------------------------------------------------- */
// Attributes: ALIGN (processed)
Area *
Heading::format(Area::size_type w, int halign) const
{
halign = get_attribute(
attributes.get(), "ALIGN", halign,
"LEFT", Area::LEFT,
"CENTER", Area::CENTER,
"RIGHT", Area::RIGHT,
0
);
static char cell_attributes[7];
if (!cell_attributes[0]) {
cell_attributes[0] = 1;
cell_attributes[1] = Formatting::getAttributes("H1.attributes", Cell::BOLD);
cell_attributes[2] = Formatting::getAttributes("H2.attributes", Cell::BOLD);
cell_attributes[3] = Formatting::getAttributes("H3.attributes", Cell::BOLD);
cell_attributes[4] = Formatting::getAttributes("H4.attributes", Cell::BOLD);
cell_attributes[5] = Formatting::getAttributes("H5.attributes", Cell::BOLD);
cell_attributes[6] = Formatting::getAttributes("H6.attributes", Cell::BOLD);
}
auto_ptr<Area> res;
auto_ptr<Line> line(::line_format(content.get()));
if (line.get()) {
static const char *prefixes[7];
if (!prefixes[1]) {
prefixes[1] = Formatting::getString("H1.prefix", "****** ");
prefixes[2] = Formatting::getString("H2.prefix", "***** " );
prefixes[3] = Formatting::getString("H3.prefix", "**** " );
prefixes[4] = Formatting::getString("H4.prefix", "*** " );
prefixes[5] = Formatting::getString("H5.prefix", "** " );
prefixes[6] = Formatting::getString("H6.prefix", "* " );
}
auto_ptr<Line> l(new Line(prefixes[level]));
l->insert(*line, l->length());
static const char *suffixes[7];
if (!suffixes[1]) {
suffixes[1] = Formatting::getString("H1.suffix", " ******");
suffixes[2] = Formatting::getString("H2.suffix", " *****" );
suffixes[3] = Formatting::getString("H3.suffix", " ****" );
suffixes[4] = Formatting::getString("H4.suffix", " ***" );
suffixes[5] = Formatting::getString("H5.suffix", " **" );
suffixes[6] = Formatting::getString("H6.suffix", " *" );
}
l->append(suffixes[level]);
l->add_attribute(cell_attributes[level]);
res.reset(make_up(*l, w, halign));
if (!res.get()) return 0;
} else {
/*
* Hm. Heading is not line-formattable...
*/
res.reset(::format(content.get(), w, halign));
if (!res.get()) return 0;
res->add_attribute(cell_attributes[level]);
}
static int vspace_before[7];
if (vspace_before[0] == 0) {
vspace_before[0] = 1;
vspace_before[1] = Formatting::getInt("H1.vspace.before", 0);
vspace_before[2] = Formatting::getInt("H2.vspace.before", 0);
vspace_before[3] = Formatting::getInt("H3.vspace.before", 0);
vspace_before[4] = Formatting::getInt("H4.vspace.before", 0);
vspace_before[5] = Formatting::getInt("H5.vspace.before", 0);
vspace_before[6] = Formatting::getInt("H6.vspace.before", 0);
}
res->prepend(vspace_before[level]);
static int vspace_after[7];
if (vspace_after[0] == 0) {
vspace_after[0] = 1;
vspace_after[1] = Formatting::getInt("H1.vspace.after", 0);
vspace_after[2] = Formatting::getInt("H2.vspace.after", 0);
vspace_after[3] = Formatting::getInt("H3.vspace.after", 0);
vspace_after[4] = Formatting::getInt("H4.vspace.after", 0);
vspace_after[5] = Formatting::getInt("H5.vspace.after", 0);
vspace_after[6] = Formatting::getInt("H6.vspace.after", 0);
}
res->append(vspace_after[level]);
return res.release();
}
// Attributes: WIDTH (processed)
Area *
Preformatted::format(Area::size_type w, int halign) const
{
w = get_attribute(attributes.get(), "WIDTH", w);
static BlockFormat bf("PRE");
/*
* Attempt to line-format the <PRE>.
*/
auto_ptr<Area> res;
auto_ptr<Line> line(::line_format(texts.get()));
if (line.get()) {
res.reset(make_up(*line, bf.effective_width(w), halign));
}
/*
* Failed; block-format it.
*/
if (!res.get()) {
res.reset(::format(texts.get(), bf.effective_width(w), halign));
if (!res.get()) return 0;
}
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
// Attributes: ALIGN (processed)
Area *
Paragraph::format(Area::size_type w, int halign) const
{
if (!texts.get()) return 0;
halign = get_attribute(
attributes.get(), "ALIGN", halign,
"LEFT", Area::LEFT,
"CENTER", Area::CENTER,
"RIGHT", Area::RIGHT,
0
);
static BlockFormat bf("P");
Area *res = ::format(texts.get(), bf.effective_width(w), halign);
if (!res) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res;
}
// Attributes: SRC ALT (processed) ALIGN HEIGHT WIDTH BORDER HSPACE VSPACE
// USEMAP ISMAP (ignored)
Line *
Image::line_format() const
{
// new image handling - Johannes Geiger
static const char *repl_all =
Formatting::getString("IMG.replace.all");
static const char *repl_noalt =
Formatting::getString("IMG.replace.noalt");
static const char *alt_prefix =
Formatting::getString("IMG.alt.prefix", "[");
static const char *alt_suffix =
Formatting::getString("IMG.alt.suffix", "]");
if (repl_all) {
return new Line(repl_all);
}
{
bool ex;
string alt(get_attribute(attributes.get(), "ALT", &ex));
if (ex) {
if (!alt.empty()) {
replace_sgml_entities(&alt);
return new Line(alt_prefix + alt + alt_suffix);
} else {
return NULL;
}
}
}
if (repl_noalt) {
return new Line(repl_noalt);
}
{
string src(get_attribute(attributes.get(), "SRC", ""));
if (!src.empty()) return new Line('[' + src + ']');
}
return new Line("[Image]");
}
// Attributes: CODEBASE CODE (ignored) ALT (processed) NAME WIDTH HEIGHT
// (ignored) ALIGN (processed) HSPACE VSPACE (ignored)
Area *
Applet::format(Area::size_type w, int /*halign*/ ) const
{
if (content.get()) {
int halign = get_attribute(
attributes.get(), "ALIGN", Area::CENTER,
"LEFT", Area::LEFT,
"MIDDLE", Area::CENTER,
"RIGHT", Area::RIGHT,
0
);
Area *a = ::format(content.get(), w, halign);
if (a) return a;
}
{
string alt(get_attribute(attributes.get(), "ALT", ""));
if (!alt.empty()) return new Area("[Java Applet: " + alt + ']');
}
{
string code(get_attribute(attributes.get(), "CODE", ""));
if (!code.empty()) return new Area("[Java Applet " + code + ']');
}
return new Area("[Java Applet]");
}
Line *
Applet::line_format() const
{
if (content.get()) {
Line *l = ::line_format(content.get());
if (l) return l;
}
{
string alt(get_attribute(attributes.get(), "ALT", ""));
if (!alt.empty()) return new Line("[Java Applet: " + alt + ']');
}
{
string code(get_attribute(attributes.get(), "CODE", ""));
if (!code.empty()) return new Line("[Java Applet " + code + ']');
}
return new Line("[Java Applet]");
}
// Attributes: NAME HREF REL REV TITLE (ignored)
// Attributes: ALIGN (processed)
Area *
Division::format(Area::size_type w, int halign) const
{
return ::format(body_content.get(), w, get_attribute(
attributes.get(), "ALIGN", halign,
"LEFT", Area::LEFT,
"CENTER", Area::CENTER,
"RIGHT", Area::RIGHT,
0
));
}
Area *
Center::format(Area::size_type w, int /*halign*/ ) const
{
return ::format(body_content.get(), w, Area::CENTER);
}
Area *
BlockQuote::format(Area::size_type w, int halign) const
{
static BlockFormat bf("BLOCKQUOTE", 0, 0, 5, 5);
auto_ptr<Area> res(::format(
content.get(),
bf.effective_width(w), halign
));
if (!res.get()) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
Area *
Address::format(Area::size_type w, int halign) const
{
static BlockFormat bf("ADDRESS", 0, 0, 5, 5);
auto_ptr<Area> res(::format(
content.get(),
bf.effective_width(w), halign
));
if (!res.get()) return 0;
*res >>= bf.indent_left;
res->prepend(bf.vspace_before);
res->append(bf.vspace_after);
return res.release();
}
/* ------------------------------------------------------------------------- */
// Attributes: ACTION METHOD ENCTYPE (ignored)
Area *
Form::format(Area::size_type w, int halign) const
{
return content.get() ? ::format(content.get(), w, halign) : 0;
}
// Attributes: TYPE (processed) NAME (ignored) VALUE CHECKED SIZE (processed)
// MAXLENGTH (ignored) SRC (processed) ALIGN (ignored)
Line *
Input::line_format() const
{
string type = get_attribute(attributes.get(), "TYPE", "TEXT");
string name = get_attribute(attributes.get(), "NAME", "");
string value = get_attribute(attributes.get(), "VALUE", "");
bool checked = get_attribute(attributes.get(), "CHECKED", "0") != "0";
int size = get_attribute(attributes.get(), "SIZE", -1);
string src = get_attribute(attributes.get(), "SRC", "");
string res;
if (cmp_nocase(type, "TEXT") == 0) {
if (size == -1) size = 20;
if (value.empty()) value = name;
// if ((int) value.length() > size) { value.erase(size); } else
if ((int) value.length() < size) value.append(size - value.length(), ' ');
res = '[' + value + ']';
} else
if (cmp_nocase(type, "PASSWORD") == 0) {
if (size == -1) size = 20;
res = '[' + string(size, '*') + ']';
} else
if (cmp_nocase(type, "CHECKBOX") == 0) {
res = checked ? '*' : LATIN1_ordm; // "ordm" looks like a superscript zero.
} else
if (cmp_nocase(type, "RADIO") == 0) {
res = checked ? '#' : 'o';
} else
if (cmp_nocase(type, "SUBMIT") == 0) {
res = value.empty() ? string("[Submit]") : '[' + value + ']';
} else
if (cmp_nocase(type, "IMAGE") == 0) {
res = "[Submit " + src + ']';
} else
if (cmp_nocase(type, "RESET") == 0) {
res = value.empty() ? string("[Reset]") : '[' + value + ']';
} else
if (cmp_nocase(type, "FILE") == 0) {
res = "[File]";
} else
if (cmp_nocase(type, "HIDDEN") == 0) {
return 0;
} else {
res = "[Unknown INPUT type]";
}
return new Line(res);
}
// Attributes: NAME SIZE (ignored) MULTIPLE (processed)
Line *
Select::line_format() const
{
if (!content.get() || content->empty()) return new Line("[Empty selection]");
bool multiple = get_attribute(attributes.get(), "MULTIPLE", "0") != "0";
auto_ptr<Line> res(new Line(multiple ? "[One or more of " : "[One of: "));
const list<auto_ptr<Option> > &c(*content);
list<auto_ptr<Option> >::const_iterator i;
for (i = c.begin(); i != c.end(); ++i) {
if (!(*i).get()) continue;
if (i != c.begin()) *res += '/';
auto_ptr<Line> l((*i)->pcdata->line_format());
*res += *l;
}
*res += ']';
return res.release();
}
// Attributes: NAME ROWS COLS
Area *
TextArea::format(Area::size_type w, int halign) const
{
auto_ptr<Line> line(pcdata->line_format());
return line.get() ? make_up(*line, w, halign) : 0;
}
/* ------------------------------------------------------------------------- */
Line *
PCData::line_format() const
{
return new Line(text);
}
// Item: Default cell attribute:
// <TT> <I> => NONE
// <B> => BOLD
// <U> => UNDERLINE
// <STRIKE> => STRIKETHROUGH
// <BIG> <SMALL> <SUB> <SUP> => NONE
static char
get_font_cell_attributes(int attribute)
{
if (attribute == HTMLParser::TT) {
static char a = Formatting::getAttributes("TT.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::I) {
static char a = Formatting::getAttributes("I.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::B) {
static char a = Formatting::getAttributes("B.attributes", Cell::BOLD);
return a;
} else
if (attribute == HTMLParser::U) {
static char a = Formatting::getAttributes("U.attributes", Cell::UNDERLINE);
return a;
} else
if (attribute == HTMLParser::STRIKE) {
static char a = Formatting::getAttributes("STRIKE.attributes", Cell::STRIKETHROUGH);
return a;
} else
if (attribute == HTMLParser::BIG) {
static char a = Formatting::getAttributes("BIG.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::SMALL) {
static char a = Formatting::getAttributes("SMALL.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::SUB) {
static char a = Formatting::getAttributes("SUB.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::SUP) {
static char a = Formatting::getAttributes("SUP.attributes", Cell::NONE);
return a;
}
return Cell::NONE;
}
Line *
Font::line_format() const
{
auto_ptr<Line> res(::line_format(texts.get()));
if (!res.get()) return 0;
char a = get_font_cell_attributes(attribute);
if (a != Cell::NONE) res->add_attribute(a);
return res.release();
}
// Item: Default cell attribute:
Area *
Font::format(Area::size_type w, int halign) const
{
auto_ptr<Area> res(::format(texts.get(), w, halign));
if (!res.get()) return 0;
char a = get_font_cell_attributes(attribute);
if (a != Cell::NONE) res->add_attribute(a);
return res.release();
}
// Item: Default cell attribute:
// <EM> <STRONG> => BOLD
// <DFN> <CODE> <SAMP> <KBD> <VAR> <CITE> => NONE
static char
get_phrase_cell_attributes(int attribute)
{
if (attribute == HTMLParser::EM) {
static char a = Formatting::getAttributes("EM.attributes", Cell::BOLD);
return a;
} else
if (attribute == HTMLParser::STRONG) {
static char a = Formatting::getAttributes("STRONG.attributes", Cell::BOLD);
return a;
} else
if (attribute == HTMLParser::DFN) {
static char a = Formatting::getAttributes("DFN.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::CODE) {
static char a = Formatting::getAttributes("CODE.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::SAMP) {
static char a = Formatting::getAttributes("SAMP.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::KBD) {
static char a = Formatting::getAttributes("KBD.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::VAR) {
static char a = Formatting::getAttributes("VAR.attributes", Cell::NONE);
return a;
} else
if (attribute == HTMLParser::CITE) {
static char a = Formatting::getAttributes("CITE.attributes", Cell::NONE);
return a;
}
return Cell::NONE;
}
Line *
Phrase::line_format() const
{
auto_ptr<Line> res(::line_format(texts.get()));
if (!res.get()) return 0;
char a = get_phrase_cell_attributes(attribute);
if (a != Cell::NONE) res->add_attribute(a);
return res.release();
}
// EM STRONG => BOLD
// DFN CODE SAMP KBD VAR CITE => (nothing)
Area *
Phrase::format(Area::size_type w, int halign) const
{
auto_ptr<Area> res(::format(texts.get(), w, halign));
if (!res.get()) return 0;
char a = get_phrase_cell_attributes(attribute);
if (a != Cell::NONE) res->add_attribute(a);
return res.release();
}
// Attributes: SIZE COLOR (ignored)
Area *
Font2::format(Area::size_type w, int halign) const
{
return ::format(elements.get(), w, halign);
}
// Attributes: SIZE COLOR (ignored)
Line *
Font2::line_format() const
{
return ::line_format(elements.get());
}
static char
get_link_cell_attributes(const string &href)
{
if (href.at(0) == '#') {
static const char internal_link_attributes =
Formatting::getAttributes("A.attributes.internal_link", Cell::UNDERLINE);
return internal_link_attributes;
} else {
static const char external_link_attributes =
Formatting::getAttributes("A.attributes.external_link", Cell::UNDERLINE);
return external_link_attributes;
}
}
// Attributes: NAME HREF REL REV TITLE (ignored)
Line *
Anchor::line_format() const
{
auto_ptr<Line> res(::line_format(texts.get()));
if (!res.get()) return 0;
string href(get_attribute(attributes.get(), "HREF", ""));
if (!href.empty()) res->add_attribute(get_link_cell_attributes(href));
return res.release();
}
Area *
Anchor::format(Area::size_type w, int halign) const
{
auto_ptr<Area> res(::format(texts.get(), w, halign));
if (!res.get()) return 0;
string href(get_attribute(attributes.get(), "HREF", ""));
if (!href.empty()) res->add_attribute(get_link_cell_attributes(href));
return res.release();
}
// Attributes: CLEAR (ignored)
Line *
LineBreak::line_format() const
{
return new Line("\n");
}
Area *
TableHeadingCell::format(Area::size_type w, int halign) const
{
Area *a = TableCell::format(w, halign);
if (a) a->add_attribute(Cell::BOLD);
return a;
}
Area *
Caption::format(Area::size_type w, int halign) const
{
auto_ptr<Line> l(::line_format(texts.get()));
return l.get() ? make_up(*l, w, halign) : 0;
}
// Attributes: (none)
Line *
NoBreak::line_format() const
{
Line *l(::line_format(content.get()));
if (!l) return 0;
for (Line::size_type i = 0; i < l->length(); ++i) {
Cell &c((*l)[i]);
if (c.character == ' ') c.character = LATIN1_nbsp;
}
return l;
}
/* ------------------------------------------------------------------------- */
/*
* Make up "line" into an Area. Attempt to return an Area no wider than "w".
*/
static Area *
make_up(const Line &line, Area::size_type w, int halign)
{
//{
// cout << "make_up(\"";
// for (Line::size_type i = 0; i < line.length(); i++) {
// if (isprint(line[i].character)) cout << line[i].character;
// else cout << "[" << (int) line[i].character << "]";
// }
// cout << "\")" << endl;
//}
if (line.empty()) return 0;
auto_ptr<Area> res(new Area);
Line::size_type from = 0;
while (from < line.length()) {
/*
* A sole newline character has a special meaning: Append a blank line.
*/
if (line[from].character == '\n') {
res->resize(res->width(), res->height() + 1);
from++;
continue;
}
Line::size_type to = from + 1;
Line::size_type lbp = (Line::size_type) -1; // "Last break position".
/*
* Determine the line break position.
*/
while (to < line.length()) {
if (line[to].character == '\n') {
break;
}
char c1 = line[to].character, c2 = line[to - 1].character;
if (c1 == ' ' || c1 == '('/*)*/ || c1 == '['/*]*/ || c1 == '{'/*}*/ || (
(
c2 == '-' ||
c2 == '/' ||
c2 == ':'
) &&
c1 != ',' &&
c1 != '.' &&
c1 != ';' &&
c1 != ':'
)) {
lbp = to++;
while (to < line.length() && line[to].character == ' ') to++;
} else {
to++;
}
if (to - from > w && lbp != (Area::size_type) -1) { to = lbp; break; }
}
/*
* Copy the "from...to" range from the "line" to the bottom of the "res"
* Area.
*/
Area::size_type x = 0;
Area::size_type len = to - from;
if (halign == Area::LEFT || len >= w) { ; } else
if (halign == Area::CENTER) { x += (w - len) / 2; } else
if (halign == Area::RIGHT) { x += w - len; }
res->insert(line.cells() + from, len, x, res->height());
/*
* Determine the beginnning of the next line.
*/
if (to == line.length()) break;
from = to;
if (line[from].character == '\n') {
++from;
} else
if (line[from].character == ' ') {
do {
++from;
} while (from < line.length() && line[from].character == ' ');
}
}
return res.release();
}
/* ------------------------------------------------------------------------- */
/*
* Attempt to line-format all "elements". If one of the elements can only be
* area-formatted, return null. In that case, "::format()" (below) will
* probably work.
*/
static Line *
line_format(const list<auto_ptr<Element> > *elements)
{
auto_ptr<Line> res;
if (elements) {
list<auto_ptr<Element> >::const_iterator i;
for (i = elements->begin(); i != elements->end(); ++i) {
auto_ptr<Line> l((*i)->line_format());
if (!l.get()) return 0;
if (res.get()) { *res += *l; } else { res = l; }
}
}
return res.release();
}
/* ------------------------------------------------------------------------- */
/*
* Basically, a list of "Text"s is a stream of words that has to be formatted
* into an area. But... as an extension to HTML 3.2 we want to allow "Block"s
* be embedded in "Text", e.g.
*
* <FONT COLOR=red><P>Bla</P><P>Bloh</P></FONT>
*
* Attempt to line-format the "Text". This will fail if there is a "Block"
* inside the "Text".
*
* The "Text" could not be line-formatted, so... append a line-break and
* the area-formatted "Text".
*/
static Area *
format(
const list<auto_ptr<Element> > *elements,
Area::size_type w,
int halign
)
{
if (!elements) return 0;
auto_ptr<Area> res;
auto_ptr<Line> line;
list<auto_ptr<Element> >::const_iterator i;
for (i = elements->begin(); i != elements->end(); ++i) {
if (!(*i).get()) continue;
auto_ptr<Line> l((*i)->line_format());
if (l.get()) {
if (line.get()) { *line += *l; } else { line = l; }
continue;
}
auto_ptr<Area> a((*i)->format(w, halign));
if (a.get()) {
if (line.get()) {
auto_ptr<Area> a2(make_up(*line, w, halign));
if (a2.get()) {
if (res.get()) { *res += *a2; } else { res = a2; }
}
line.reset();
}
if (res.get()) { *res += *a; } else { res = a; }
}
}
if (line.get()) {
auto_ptr<Area> a2(make_up(*line, w, halign));
if (a2.get()) {
if (res.get()) { *res += *a2; } else { res = a2; }\
}
}
return res.release();
}
/*
* A copy of the above function, but the formatted text is printed to "os"
* rather than into an Area.
*/
static void
format(
const list<auto_ptr<Element> > *elements,
Area::size_type indent_left,
Area::size_type w,
int halign,
ostream &os
)
{
if (!elements) return;
auto_ptr<Line> line;
list<auto_ptr<Element> >::const_iterator i;
for (i = elements->begin(); i != elements->end(); ++i) {
if (!(*i).get()) continue;
auto_ptr<Line> l((*i)->line_format());
if (l.get()) {
if (line.get()) { *line += *l; } else { line = l; }
continue;
}
auto_ptr<Area> a((*i)->format(w, halign));
if (a.get()) {
if (line.get()) {
auto_ptr<Area> a2(make_up(*line, w, halign));
if (a2.get()) {
*a2 >>= indent_left;
os << *a2 << flush;
}
line.reset();
}
*a >>= indent_left;
os << *a << flush;
}
}
if (line.get()) {
auto_ptr<Area> a2(make_up(*line, w, halign));
if (a2.get()) {
*a2 >>= indent_left;
os << *a2 << flush;
}
}
}
/* ------------------------------------------------------------------------- */
static Properties formatting_properties;
/* ----------------------- */
/*static*/ void
Formatting::setProperty(const char *key, const char *value)
{
formatting_properties.setProperty(key, value);
}
/* ----------------------- */
/*static*/ void
Formatting::loadProperties(istream &is)
{
formatting_properties.load(is);
}
/* ----------------------- */
/*static*/ const char *
Formatting::getString(const char *key, const char *dflt)
{
return formatting_properties.getProperty(key, dflt);
}
// neue Methode fuer leere Attribute - Johannes Geiger
const char *
Formatting::getString(const char *key)
{
return formatting_properties.getProperty(key);
}
/* ----------------------- */
/*
* Property not set => 0
* Property contains only white-space => 0
* Property conains one non-white-space character => { "x" }
*/
/*static*/ vector<string> *
Formatting::getStringVector(const char *key, const char *dflt)
{
const char *p = formatting_properties.getProperty(key, dflt);
if (!p) return 0;
vector<string> *res = 0;
for (;;) {
while (isspace(*p)) ++p;
if (!*p) break;
const char *q = p + 1;
while (*q && !isspace(*q)) ++q;
if (!res) res = new vector<string>;
res->push_back(string(p, q - p));
p = q;
}
return res;
}
/* ----------------------- */
/*static*/ int
Formatting::getInt(const char *key, int dflt)
{
const char *p = formatting_properties.getProperty(key, 0);
return p ? atoi(p) : dflt;
}
/* ----------------------- */
/*static*/ vector<int> *
Formatting::getIntVector(const char *key, const char *dflt)
{
const char *p = formatting_properties.getProperty(key, dflt);
if (!p) return 0;
vector<int> *res = 0;
for (;;) {
while (isspace(*p)) ++p;
if (!*p) break;
if (!res) res = new vector<int>;
res->push_back(atoi(p));
++p;
while (*p && !isspace(*p)) ++p;
}
return res;
}
/* ----------------------- */
/*static*/ char
Formatting::getAttributes(const char *key, char dflt)
{
auto_ptr<vector<string> > v(getStringVector(key, 0));
if (!v.get() || v->empty()) return dflt;
char res = Cell::NONE;
for (vector<string>::const_iterator i = v->begin(); i != v->end(); ++i) {
if (!cmp_nocase(*i, "NONE")) res = Cell::NONE;
else if (!cmp_nocase(*i, "BOLD")) res |= Cell::BOLD;
else if (!cmp_nocase(*i, "UNDERLINE")) res |= Cell::UNDERLINE;
else if (!cmp_nocase(*i, "STRIKETHROUGH")) res |= Cell::STRIKETHROUGH;
else ;
}
return res;
}
/* ------------------------------------------------------------------------- */
BlockFormat::BlockFormat(
const char *item_name,
Area::size_type default_vspace_before /* = 0 */ ,
Area::size_type default_vspace_after /* = 0 */ ,
Area::size_type default_indent_left /* = 0 */ ,
Area::size_type default_indent_right /* = 0 */
)
{
char lb[80];
sprintf(lb, "%s.vspace.before", item_name);
vspace_before = Formatting::getInt(lb, default_vspace_before);
sprintf(lb, "%s.vspace.after", item_name);
vspace_after = Formatting::getInt(lb, default_vspace_after);
sprintf(lb, "%s.indent.left", item_name);
indent_left = Formatting::getInt(lb, default_indent_left);
sprintf(lb, "%s.indent.right", item_name);
indent_right = Formatting::getInt(lb, default_indent_right);
}
Area::size_type
BlockFormat::effective_width(Area::size_type w) const
{
/*
* No problem if "w" is wide enough...
*/
if (indent_left + 10 + indent_right <= w) {
return w - indent_left - indent_right;
}
/*
* Does reducing the right indent help?
*/
if (indent_left + 10 <= w) return 10;
/*
* Do it with right indent == 0.
*/
if (indent_left + 1 <= w) return w - indent_left;
/*
* Even that doesn't help, return "1".
*/
return 1;
}
/* ------------------------------------------------------------------------- */
ListFormat::ListFormat(
const char *item_name,
Area::size_type default_vspace_before /* = 0 */ ,
Area::size_type default_vspace_between /* = 0 */ ,
Area::size_type default_vspace_after /* = 0 */ ,
const char *default_indents /* = "6" */ ,
const char *default_default_types /* = "DISC CIRCLE SQUARE" */
)
{
char lb[80];
sprintf(lb, "%s.vspace.before", item_name);
vspace_before = Formatting::getInt(lb, default_vspace_before );
sprintf(lb, "%s.vspace.between", item_name);
vspace_between = Formatting::getInt(lb, default_vspace_between);
sprintf(lb, "%s.vspace.after", item_name);
vspace_after = Formatting::getInt(lb, default_vspace_after );
sprintf(lb, "%s.indents", item_name);
indents.reset(Formatting::getIntVector(lb, default_indents));
sprintf(lb, "%s.default_types", item_name);
default_types.reset(Formatting::getStringVector(lb, default_default_types));
}
Area::size_type
ListFormat::get_indent(int nesting) const
{
return (
(!indents.get() || indents.get()->empty()) ? 6 :
nesting < indents->size() ? (*indents)[nesting] :
indents->back()
);
}
int
ListFormat::get_type(
const list<TagAttribute> *attributes,
int nesting,
int default_default_type
) const
{
const char *default_type = (
!default_types.get() || default_types->empty() ? 0 :
nesting < default_types->size() ?
(*default_types)[nesting].c_str() :
default_types->back().c_str()
);
return get_attribute(
attributes, "TYPE",
default_type, // dflt1
default_default_type, // dflt2, if dflt1 fails
"NO_BULLET", NO_BULLET,
"DISC", DISC,
"SQUARE", SQUARE,
"CIRCLE", CIRCLE,
"CUSTOM1", CUSTOM1,
"CUSTOM2", CUSTOM2,
"CUSTOM3", CUSTOM3,
"1", ARABIC_NUMBERS,
"a", LOWER_ALPHA,
"A", UPPER_ALPHA,
"i", LOWER_ROMAN,
"I", UPPER_ROMAN,
0
);
}
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/format.h 0100644 0000000 0000000 00000004610 07760112171 013754 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Fre Jun 8 17:49:39 CEST 2001: new method
* Thu Oct 4 21:36:51 CEST 2001: ported to g++ 3.0
* Wed Jul 2 22:05:32 CEST 2003: ported to g++ 3.3
*/
/***************************************************************************/
#ifndef __format_h_INCLUDED__ /* { */
#define __format_h_INCLUDED__
/* ------------------------------------------------------------------------- */
#include <string>
#include <vector>
#include <istream>
using std::string;
using std::vector;
using std::istream;
/* ------------------------------------------------------------------------- */
class Formatting {
public:
static void setProperty(const char *key, const char *value);
static void loadProperties(istream &is);
static const char *getString(const char *key, const char *dflt);
// neue Methode fuer leere Attribute - Johannes Geiger
static const char *getString(const char *key);
static vector<string> *getStringVector(const char *key, const char *dflt);
static int getInt(const char *key, int dflt);
static vector<int> * getIntVector(const char *key, const char *dflt);
static char getAttributes(const char *key, char dflt);
private:
Formatting(); // Do not instantiate me!
};
/* ------------------------------------------------------------------------- */
#endif /* } */
/* ------------------------------------------------------------------------- */
html2text-1.3.2a/html.C 0100644 0000000 0000000 00000040364 07760112171 013371 0 ustar root root
/***************************************************************************/
/*
* Portions Copyright (c) 1999 GMRS Software GmbH
* Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
* All rights reserved.
*
* Author: Arno Unkrig <arno@unkrig.de>
*/
/* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License in the file COPYING for more details.
*/
/***************************************************************************/
/*
* Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
* Dates and reasons of modifications:
* Fre Jun 8 17:43:02 CEST 2001: new method
* Wed Jul 2 22:07:12 CEST 2003: ported to g++ 3.3
*/
/***************************************************************************/
#include <stdlib.h>
#include <stdarg.h>
#include <iostream>
#include "html.h"
#include "HTMLParser.h"
#include "cmp_nocase.h"
/* ------------------------------------------------------------------------- */
/*
* Define some helpers.
*/
#define define_foreach(T, args, action) \
void foreach args { \
for (T::const_iterator i = l.begin(); i != l.end(); ++i) { \
action; \
} \
}
#define pack(T) \
define_foreach(list<auto_ptr<T> >, ( \
const list<auto_ptr<T> > &l, \
ostream &os, \
ostream_manipulator separator \
), (*i)->unparse(os, separator))
static pack(Element)
static pack(TableCell)
static pack(TableRow)
static pack(ListItem)
static pack(Option)
static pack(DefinitionListItem)
static pack(Script)
static pack(Style)
#undef pack
/*
* Special helper for "const auto_ptr<list<TagAttribute> > &".
*/
static ostream &operator<<(ostream &os, const auto_ptr<list<TagAttribute> > &a)
{
if (a.get()) {
const list<TagAttribute> &al(*a);
list<TagAttribute>::const_iterator i;
for (i = al.begin(); i != al.end(); ++i) {
os << " " << (*i).first << "=\"" << (*i).second << "\"";
}
}
return os;
}
/* ------------------------------------------------------------------------- */
/*
* Brothers of "endl".
*/
static ostream &none(ostream &os) { return os; }
/* ------------------------------------------------------------------------- */
/*
* Some C++ compilers (e.g. EGCS 2.91.66) have problems if all virtual
* methods of a class are inline or pure virtual, so we define the virtual
* "Element::~Element()", which is the only virtual method, non-inline,
* although it is empty.
*/
Element::~Element()
{
}
/* ------------------------------------------------------------------------- */
void
Document::unparse(ostream &os, ostream_manipulator separator) const
{
os << "<HTML" << attributes << ">" << separator;
head.unparse(os, separator);
body.unparse(os, separator);
os << "</HTML>" << separator;
}
void
Head::unparse(ostream &os, ostream_manipulator separator) const
{
os << "<HEAD>" << separator;
if (title.get()) {
os << "<TITLE>" << separator;
title->unparse(os, separator);
os << "" << separator;
}
if (isindex_attributes.get()) {
os << "" << std::endl;
}
if (base_attributes.get()) os << "" << std::endl;
foreach(scripts, os, separator);
foreach(styles, os, separator);
if (meta_attributes.get()) os << "" << std::endl;
if (link_attributes.get()) os << "" << std::endl;
os << "" << separator;
}
void
Script::unparse(ostream &os, ostream_manipulator separator) const
{
os
<< "" << separator
<< text
<< "" << separator;
}
void
Style::unparse(ostream &os, ostream_manipulator separator) const
{
os
<< "" << separator
<< text
<< "" << separator;
}
void
Body::unparse(ostream &os, ostream_manipulator separator) const
{
os << "" << separator;
if (content.get()) foreach(*content, os, separator);
os << "