diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 17:04:52 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 17:04:52 +0000 |
commit | 5e03c718f4e7ff13cb6834eda737c269ebed02ad (patch) | |
tree | bfad3f5be123f000fdb03e26400050dece33d72f /src/html-parse.h | |
parent | Initial commit. (diff) | |
download | wget-upstream.tar.xz wget-upstream.zip |
Adding upstream version 1.21.3.upstream/1.21.3upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/html-parse.h')
-rw-r--r-- | src/html-parse.h | 71 |
1 files changed, 71 insertions, 0 deletions
diff --git a/src/html-parse.h b/src/html-parse.h new file mode 100644 index 0000000..4176eb2 --- /dev/null +++ b/src/html-parse.h @@ -0,0 +1,71 @@ +/* Declarations for html-parse.c. + Copyright (C) 1998-2011, 2015, 2018-2022 Free Software Foundation, + Inc. + +This file is part of GNU Wget. + +GNU Wget 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 3 of the License, or + (at your option) any later version. + +GNU Wget 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 Wget. If not, see <http://www.gnu.org/licenses/>. + +Additional permission under GNU GPL version 3 section 7 + +If you modify this program, or any covered work, by linking or +combining it with the OpenSSL project's OpenSSL library (or a +modified version of that library), containing parts covered by the +terms of the OpenSSL or SSLeay licenses, the Free Software Foundation +grants you additional permission to convey the resulting work. +Corresponding Source for a non-source form of such a combination +shall include the source code for the parts of OpenSSL used as well +as that of the covered work. */ + +#ifndef HTML_PARSE_H +#define HTML_PARSE_H + +struct attr_pair { + char *name; /* attribute name */ + char *value; /* attribute value */ + + /* Needed for URL conversion; the places where the value begins and + ends, including the quotes and everything. */ + const char *value_raw_beginning; + int value_raw_size; + + /* Used internally by map_html_tags. */ + int name_pool_index, value_pool_index; +}; + +struct taginfo { + char *name; /* tag name */ + int end_tag_p; /* whether this is an end-tag */ + int nattrs; /* number of attributes */ + struct attr_pair *attrs; /* attributes */ + + const char *start_position; /* start position of tag */ + const char *end_position; /* end position of tag */ + + const char *contents_begin; /* delimiters of tag contents */ + const char *contents_end; /* only valid if end_tag_p */ +}; + +struct hash_table; /* forward declaration */ + +/* Flags for map_html_tags: */ +#define MHT_STRICT_COMMENTS 1 /* use strict comment interpretation */ +#define MHT_TRIM_VALUES 2 /* trim attribute values, e.g. interpret + <a href=" foo "> as "foo" */ + +void map_html_tags (const char *, int, + void (*) (struct taginfo *, void *), void *, int, + const struct hash_table *, const struct hash_table *); + +#endif /* HTML_PARSE_H */ |