On 11 Apr 2002 at 21:00, Hrvoje Niksic wrote:
> This change is fine with me. I vaguely remember that this test is
> performed in two places; you might want to create a function.
I've found three places where it checks the suffix, so I called a
new function in all three places for consistency. One of those
places performed a case-insensitive comparison so I made my
function do that too.
Hrvoje, you may wish to review whether checking the new extensions
in all three places (but particularly recur.c) is a good idea or
not before I commit the patch.
src/ChangeLog entry:
2002-04-12 Ian Abbott <[EMAIL PROTECTED]>
* utils.c (has_html_suffix_p): New function to text filename for common
html extensions.
* utils.h: Declare it.
* http.c (http_loop): Use it instead of previous test.
* retr.c (retrieve_url): Ditto.
* recur.c (download_child_p): Ditto.
Index: src/http.c
===================================================================
RCS file: /pack/anoncvs/wget/src/http.c,v
retrieving revision 1.86
diff -u -r1.86 http.c
--- src/http.c 2002/04/11 17:49:32 1.86
+++ src/http.c 2002/04/12 17:35:02
@@ -1405,7 +1405,7 @@
int use_ts, got_head = 0; /* time-stamping info */
char *filename_plus_orig_suffix;
char *local_filename = NULL;
- char *tms, *suf, *locf, *tmrate;
+ char *tms, *locf, *tmrate;
uerr_t err;
time_t tml = -1, tmr = -1; /* local and remote time-stamps */
long local_size = 0; /* the size of the local file */
@@ -1465,9 +1465,8 @@
*dt |= RETROKF;
/* #### Bogusness alert. */
- /* If its suffix is "html" or "htm", assume text/html. */
- if (((suf = suffix (*hstat.local_file)) != NULL)
- && (!strcmp (suf, "html") || !strcmp (suf, "htm")))
+ /* If its suffix is "html" or "htm" or similar, assume text/html. */
+ if (has_html_suffix_p (*hstat.local_file))
*dt |= TEXTHTML;
FREE_MAYBE (dummy);
Index: src/recur.c
===================================================================
RCS file: /pack/anoncvs/wget/src/recur.c,v
retrieving revision 1.43
diff -u -r1.43 recur.c
--- src/recur.c 2002/02/19 06:09:57 1.43
+++ src/recur.c 2002/04/12 17:35:02
@@ -510,7 +510,6 @@
/* 6. */
{
- char *suf;
/* Check for acceptance/rejection rules. We ignore these rules
for HTML documents because they might lead to other files which
need to be downloaded. Of course, we don't know which
@@ -521,14 +520,13 @@
* u->file is not "" (i.e. it is not a directory)
and either:
+ there is no file suffix,
- + or there is a suffix, but is not "html" or "htm",
+ + or there is a suffix, but is not "html" or "htm" or similar,
+ both:
- recursion is not infinite,
- and we are at its very end. */
if (u->file[0] != '\0'
- && ((suf = suffix (url)) == NULL
- || (0 != strcmp (suf, "html") && 0 != strcmp (suf, "htm"))
+ && (!has_html_suffix_p (url)
|| (opt.reclevel != INFINITE_RECURSION && depth >= opt.reclevel)))
{
if (!acceptable (u->file))
Index: src/retr.c
===================================================================
RCS file: /pack/anoncvs/wget/src/retr.c,v
retrieving revision 1.50
diff -u -r1.50 retr.c
--- src/retr.c 2002/01/30 19:12:20 1.50
+++ src/retr.c 2002/04/12 17:35:03
@@ -384,12 +384,11 @@
/* There is a possibility of having HTTP being redirected to
FTP. In these cases we must decide whether the text is HTML
- according to the suffix. The HTML suffixes are `.html' and
- `.htm', case-insensitive. */
+ according to the suffix. The HTML suffixes are `.html',
+ `.htm' and a few others, case-insensitive. */
if (redirection_count && local_file && u->scheme == SCHEME_FTP)
{
- char *suf = suffix (local_file);
- if (suf && (!strcasecmp (suf, "html") || !strcasecmp (suf, "htm")))
+ if (has_html_suffix_p (local_file))
*dt |= TEXTHTML;
}
}
Index: src/utils.c
===================================================================
RCS file: /pack/anoncvs/wget/src/utils.c,v
retrieving revision 1.44
diff -u -r1.44 utils.c
--- src/utils.c 2002/01/17 01:03:33 1.44
+++ src/utils.c 2002/04/12 17:35:03
@@ -792,6 +792,30 @@
return NULL;
}
+/* Checks whether a filename is has a typical HTML suffix or not. The
+ following suffixes are presumed to be html files (case insensitive):
+
+ html
+ htm
+ ?html (where ? is any character)
+
+ This is not necessarily a good indication that the file actually contains
+ HTML! */
+int has_html_suffix_p (const char *fname)
+{
+ char *suf;
+
+ if ((suf = suffix (fname)) == NULL)
+ return 0;
+ if (!strcasecmp (suf, "html"))
+ return 1;
+ if (!strcasecmp (suf, "htm"))
+ return 1;
+ if (suf[0] && !strcasecmp (suf + 1, "html"))
+ return 1;
+ return 0;
+}
+
/* Read a line from FP and return the pointer to freshly allocated
storage. The stoarage space is obtained through malloc() and
should be freed with free() when it is no longer needed.
Index: src/utils.h
===================================================================
RCS file: /pack/anoncvs/wget/src/utils.h,v
retrieving revision 1.17
diff -u -r1.17 utils.h
--- src/utils.h 2001/12/17 14:05:08 1.17
+++ src/utils.h 2002/04/12 17:35:03
@@ -70,6 +70,8 @@
char *suffix PARAMS ((const char *s));
int match_tail PARAMS ((const char *, const char *));
+int has_html_suffix_p PARAMS ((const char *));
+
char *read_whole_line PARAMS ((FILE *));
struct file_memory *read_file PARAMS ((const char *));
void read_file_free PARAMS ((struct file_memory *));
