From 89b37c7eff60d6e5e233330956049cea1807ad27 Mon Sep 17 00:00:00 2001 From: hniksic Date: Mon, 27 May 2002 08:03:35 -0700 Subject: [PATCH] [svn] Allow almost any character in attribute/tag names. --- src/ChangeLog | 4 ++++ src/html-parse.c | 27 ++++++++++++++++++++------- 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/src/ChangeLog b/src/ChangeLog index 98408664..f3ba5f0f 100644 --- a/src/ChangeLog +++ b/src/ChangeLog @@ -1,3 +1,7 @@ +2002-05-27 Hrvoje Niksic + + * html-parse.c (NAME_CHAR_P): Allow almost any character here. + 2002-05-24 Hrvoje Niksic * progress.c (bar_set_params): Fall back to dot progress if the diff --git a/src/html-parse.c b/src/html-parse.c index 8cdcd692..74d34440 100644 --- a/src/html-parse.c +++ b/src/html-parse.c @@ -344,10 +344,23 @@ array_allowed (const char **array, const char *beg, const char *end) return 1; } -/* RFC1866: name [of attribute or tag] consists of letters, digits, - periods, or hyphens. We also allow _, for compatibility with - brain-damaged generators. */ -#define NAME_CHAR_P(x) (ISALNUM (x) || (x) == '.' || (x) == '-' || (x) == '_') +/* Originally we used to adhere to RFC1866 here, and allowed only + letters, digits, periods, and hyphens as names (of tags or + attributes). However, this broke too many pages which used + proprietary or strange attributes, e.g. . + + So now we allow any character except: + * whitespace + * 8-bit and control chars + * characters that clearly cannot be part of name: + '=', '>', '/'. + + This only affects attribute and tag names; attribute values allow + an even greater variety of characters. */ + +#define NAME_CHAR_P(x) ((x) > 32 && (x) < 127 \ + && (x) != '=' && (x) != '>' && (x) != '/') /* States while advancing through comments. */ #define AC_S_DONE 0 @@ -450,10 +463,10 @@ advance_declaration (const char *beg, const char *end) } break; case AC_S_DCLNAME: - if (NAME_CHAR_P (ch)) - ch = *p++; - else if (ch == '-') + if (ch == '-') state = AC_S_DASH1; + else if (NAME_CHAR_P (ch)) + ch = *p++; else state = AC_S_DEFAULT; break; -- 2.39.2