Replaced read_whole_file(), which needs one malloc/free per line, by getline()
which reuses a growable buffer.
getline() is a GNU function (but Wget is a GNU tool, isn't it ? :-).
Since Wget compiles/links with gnulib, I don't see a problem here.
Regards, Tim
From eeffb62ba0a13c5c20ddd66492c7774e0f713237 Mon Sep 17 00:00:00 2001
From: Tim Ruehsen <tim.rueh...@gmx.de>
Date: Thu, 9 May 2013 22:37:17 +0200
Subject: [PATCH 2/3] replaced read_whole_file() by getline()
---
src/ChangeLog | 5 ++
src/cookies.c | 9 +++-
src/ftp-ls.c | 148 +++++++++++++++++++++++----------------------------------
src/ftp.c | 16 ++++---
src/init.c | 7 +--
src/netrc.c | 50 ++-----------------
src/utils.c | 50 -------------------
src/utils.h | 1 -
8 files changed, 89 insertions(+), 197 deletions(-)
diff --git a/src/ChangeLog b/src/ChangeLog
index 84a9645..3b6733e 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,5 +1,10 @@
2013-05-09 Tim Ruehsen <tim.rueh...@gmx.de>
+ * cookies.c, ftp-ls.c, ftp.c, init.c, netrc.c, utils.c, utils.h:
+ replaced read_whole_file() by getline().
+
+2013-05-09 Tim Ruehsen <tim.rueh...@gmx.de>
+
* utils.c: use standard string functions instead of self-written
code in acceptable(), match_tail(), suffix(), has_wildcards_p().
Avoid some warnings in test code.
diff --git a/src/cookies.c b/src/cookies.c
index 87cc554..4efda88 100644
--- a/src/cookies.c
+++ b/src/cookies.c
@@ -1129,7 +1129,9 @@ domain_port (const char *domain_b, const char *domain_e,
void
cookie_jar_load (struct cookie_jar *jar, const char *file)
{
- char *line;
+ char *line = NULL;
+ size_t bufsize = 0;
+
FILE *fp = fopen (file, "r");
if (!fp)
{
@@ -1137,9 +1139,10 @@ cookie_jar_load (struct cookie_jar *jar, const char *file)
quote (file), strerror (errno));
return;
}
+
cookies_now = time (NULL);
- for (; ((line = read_whole_line (fp)) != NULL); xfree (line))
+ while (getline (&line, &bufsize, fp) > 0)
{
struct cookie *cookie;
char *p = line;
@@ -1233,6 +1236,8 @@ cookie_jar_load (struct cookie_jar *jar, const char *file)
abort_cookie:
delete_cookie (cookie);
}
+
+ xfree(line);
fclose (fp);
}
diff --git a/src/ftp-ls.c b/src/ftp-ls.c
index 3056651..401ae77 100644
--- a/src/ftp-ls.c
+++ b/src/ftp-ls.c
@@ -68,16 +68,17 @@ symperms (const char *s)
replaces all <TAB> character with <SPACE>. Returns the length of the
modified line. */
static int
-clean_line(char *line)
+clean_line(char *line, int len)
{
- int len = strlen (line);
- if (!len) return 0;
- if (line[len - 1] == '\n')
+ if (len <= 0) return 0;
+
+ while (len > 0 && (line[len - 1] == '\n' || line[len - 1] == '\r'))
line[--len] = '\0';
+
if (!len) return 0;
- if (line[len - 1] == '\r')
- line[--len] = '\0';
+
for ( ; *line ; line++ ) if (*line == '\t') *line = ' ';
+
return len;
}
@@ -102,8 +103,9 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
int hour, min, sec, ptype;
struct tm timestruct, *tnow;
time_t timenow;
+ size_t bufsize = 0;
- char *line, *tok, *ptok; /* tokenizer */
+ char *line = NULL, *tok, *ptok; /* tokenizer */
struct fileinfo *dir, *l, cur; /* list creation */
fp = fopen (file, "rb");
@@ -115,22 +117,16 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
dir = l = NULL;
/* Line loop to end of file: */
- while ((line = read_whole_line (fp)) != NULL)
+ while ((len = getline (&line, &bufsize, fp)) > 0)
{
- len = clean_line (line);
+ len = clean_line (line, len);
/* Skip if total... */
if (!strncasecmp (line, "total", 5))
- {
- xfree (line);
continue;
- }
/* Get the first token (permissions). */
tok = strtok (line, " ");
if (!tok)
- {
- xfree (line);
continue;
- }
cur.name = NULL;
cur.linkto = NULL;
@@ -368,7 +364,6 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
DEBUGP (("Skipping.\n"));
xfree_null (cur.name);
xfree_null (cur.linkto);
- xfree (line);
continue;
}
@@ -416,10 +411,9 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
timestruct.tm_isdst = -1;
l->tstamp = mktime (×truct); /* store the time-stamp */
l->ptype = ptype;
-
- xfree (line);
}
+ xfree (line);
fclose (fp);
return dir;
}
@@ -431,9 +425,10 @@ ftp_parse_winnt_ls (const char *file)
int len;
int year, month, day; /* for time analysis */
int hour, min;
+ size_t bufsize = 0;
struct tm timestruct;
- char *line, *tok; /* tokenizer */
+ char *line = NULL, *tok; /* tokenizer */
char *filename;
struct fileinfo *dir, *l, cur; /* list creation */
@@ -446,29 +441,29 @@ ftp_parse_winnt_ls (const char *file)
dir = l = NULL;
/* Line loop to end of file: */
- while ((line = read_whole_line (fp)) != NULL)
+ while ((len = getline (&line, &bufsize, fp)) > 0)
{
- len = clean_line (line);
+ len = clean_line (line, len);
/* Name begins at 39 column of the listing if date presented in `mm-dd-yy'
format or at 41 column if date presented in `mm-dd-yyyy' format. Thus,
we cannot extract name before we parse date. Using this information we
also can recognize filenames that begin with a series of space
characters (but who really wants to use such filenames anyway?). */
- if (len < 40) goto continue_loop;
+ if (len < 40) continue;
filename = line + 39;
/* First column: mm-dd-yy or mm-dd-yyyy. Should atoi() on the month fail,
january will be assumed. */
tok = strtok(line, "-");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
month = atoi(tok) - 1;
if (month < 0) month = 0;
tok = strtok(NULL, "-");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
day = atoi(tok);
tok = strtok(NULL, " ");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
year = atoi(tok);
/* Assuming the epoch starting at 1.1.1970 */
if (year <= 70)
@@ -489,10 +484,10 @@ ftp_parse_winnt_ls (const char *file)
/* Second column: hh:mm[AP]M, listing does not contain value for
seconds */
tok = strtok(NULL, ":");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
hour = atoi(tok);
tok = strtok(NULL, "M");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
min = atoi(tok);
/* Adjust hour from AM/PM. Just for the record, the sequence goes
11:00AM, 12:00PM, 01:00PM ... 11:00PM, 12:00AM, 01:00AM . */
@@ -523,9 +518,9 @@ ftp_parse_winnt_ls (const char *file)
directories as the listing does not give us a clue) and filetype
here. */
tok = strtok(NULL, " ");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
while ((tok != NULL) && (*tok == '\0')) tok = strtok(NULL, " ");
- if (tok == NULL) goto continue_loop;
+ if (tok == NULL) continue;
if (*tok == '<')
{
cur.type = FT_DIRECTORY;
@@ -564,11 +559,9 @@ ftp_parse_winnt_ls (const char *file)
memcpy (l, &cur, sizeof (cur));
l->next = NULL;
}
-
-continue_loop:
- xfree (line);
}
+ xfree (line);
fclose(fp);
return dir;
}
@@ -689,11 +682,12 @@ ftp_parse_vms_ls (const char *file)
FILE *fp;
int dt, i, j, len;
int perms;
+ size_t bufsize = 0;
time_t timenow;
struct tm *timestruct;
char date_str[ 32];
- char *line, *tok; /* tokenizer */
+ char *line = NULL, *tok; /* tokenizer */
struct fileinfo *dir, *l, cur; /* list creation */
fp = fopen (file, "r");
@@ -706,52 +700,34 @@ ftp_parse_vms_ls (const char *file)
/* Skip blank lines, Directory heading, and more blank lines. */
- j = 0; /* Expecting initial blank line(s). */
- while (1)
+ for (j = 0; (i = getline (&line, &bufsize, fp)) > 0; )
{
- line = read_whole_line (fp);
- if (line == NULL)
- {
- break;
- }
- else
- {
- i = clean_line (line);
- if (i <= 0)
- {
- xfree (line); /* Free useless line storage. */
- continue; /* Blank line. Keep looking. */
- }
- else
- {
- if ((j == 0) && (line[ i- 1] == ']'))
- {
- /* Found Directory heading line. Next non-blank line
- is significant.
- */
- j = 1;
- }
- else if (!strncmp (line, "Total of ", 9))
- {
- /* Found "Total of ..." footing line. No valid data
- will follow (empty directory).
- */
- xfree (line); /* Free useless line storage. */
- line = NULL; /* Arrange for early exit. */
- break;
- }
- else
- {
- break; /* Must be significant data. */
- }
- }
- xfree (line); /* Free useless line storage. */
- }
+ i = clean_line (line, i);
+ if (i <= 0)
+ continue; /* Ignore blank line. */
+
+ if ((j == 0) && (line[i - 1] == ']'))
+ {
+ /* Found Directory heading line. Next non-blank line
+ is significant. */
+ j = 1;
+ }
+ else if (!strncmp (line, "Total of ", 9))
+ {
+ /* Found "Total of ..." footing line. No valid data
+ will follow (empty directory). */
+ i = 0; /* Arrange for early exit. */
+ break;
+ }
+ else
+ {
+ break; /* Must be significant data. */
+ }
}
/* Read remainder of file until the next blank line or EOF. */
- while (line != NULL)
+ while (i > 0)
{
char *p;
@@ -842,9 +818,8 @@ ftp_parse_vms_ls (const char *file)
if (tok == NULL)
{
DEBUGP (("Getting additional line.\n"));
- xfree (line);
- line = read_whole_line (fp);
- if (!line)
+ i = getline (&line, &bufsize, fp);
+ if (i <= 0)
{
DEBUGP (("EOF. Leaving listing parser.\n"));
break;
@@ -853,14 +828,14 @@ ftp_parse_vms_ls (const char *file)
/* Second line must begin with " ". Otherwise, it's a first
line (and we may be confused).
*/
+ i = clean_line (line, i);
if (i <= 0)
{
/* Blank line. End of significant file listing. */
DEBUGP (("Blank line. Leaving listing parser.\n"));
- xfree (line); /* Free useless line storage. */
break;
}
- else if (line[ 0] != ' ')
+ else if (line[0] != ' ')
{
DEBUGP (("Non-blank in column 1. Must be a new file name?\n"));
continue;
@@ -872,7 +847,6 @@ ftp_parse_vms_ls (const char *file)
{
/* Unexpected non-empty but apparently blank line. */
DEBUGP (("Null token. Leaving listing parser.\n"));
- xfree (line); /* Free useless line storage. */
break;
}
}
@@ -911,7 +885,7 @@ ftp_parse_vms_ls (const char *file)
(sizeof( date_str)- strlen (date_str) - 1));
DEBUGP (("Date time: >%s<\n", date_str));
}
- else if (strchr ( tok, '[') != NULL)
+ else if (strchr (tok, '[') != NULL)
{
/* Owner. (Ignore.) */
DEBUGP (("Owner.\n"));
@@ -921,7 +895,7 @@ ftp_parse_vms_ls (const char *file)
/* Protections (permissions). */
perms = 0;
j = 0;
- for (i = 0; i < strlen( tok); i++)
+ for (i = 0; i < strlen(tok); i++)
{
switch (tok[ i])
{
@@ -1015,21 +989,19 @@ ftp_parse_vms_ls (const char *file)
l->next = NULL;
}
- /* Free old line storage. Read a new line. */
- xfree (line);
- line = read_whole_line (fp);
- if (line != NULL)
+ i = getline (&line, &bufsize, fp);
+ if (i > 0)
{
- i = clean_line (line);
+ i = clean_line (line, i);
if (i <= 0)
{
/* Blank line. End of significant file listing. */
- xfree (line); /* Free useless line storage. */
break;
}
}
}
+ xfree (line);
fclose (fp);
return dir;
}
diff --git a/src/ftp.c b/src/ftp.c
index b585631..fbfbe8f 100644
--- a/src/ftp.c
+++ b/src/ftp.c
@@ -1367,18 +1367,20 @@ Error in server response, closing control connection.\n"));
logprintf (LOG_ALWAYS, "%s: %s\n", con->target, strerror (errno));
else
{
- char *line;
- /* The lines are being read with read_whole_line because of
+ char *line = NULL;
+ size_t bufsize = 0;
+ ssize_t len;
+
+ /* The lines are being read with getline because of
no-buffering on opt.lfile. */
- while ((line = read_whole_line (fp)) != NULL)
+ while ((len = getline (&line, &bufsize, fp)) > 0)
{
- char *p = strchr (line, '\0');
- while (p > line && (p[-1] == '\n' || p[-1] == '\r'))
- *--p = '\0';
+ while (len > 0 && (line[len - 1] == '\n' || line[len - 1] == '\r'))
+ line[--len] = '\0';
logprintf (LOG_ALWAYS, "%s\n",
quotearg_style (escape_quoting_style, line));
- xfree (line);
}
+ xfree (line);
fclose (fp);
}
} /* con->cmd & DO_LIST && server_response */
diff --git a/src/init.c b/src/init.c
index 0c41825..54a2919 100644
--- a/src/init.c
+++ b/src/init.c
@@ -574,7 +574,8 @@ bool
run_wgetrc (const char *file)
{
FILE *fp;
- char *line;
+ char *line = NULL;
+ size_t bufsize = 0;
int ln;
int errcnt = 0;
@@ -586,7 +587,7 @@ run_wgetrc (const char *file)
return true; /* not a fatal error */
}
ln = 1;
- while ((line = read_whole_line (fp)) != NULL)
+ while (getline (&line, &bufsize, fp) > 0)
{
char *com = NULL, *val = NULL;
int comind;
@@ -620,9 +621,9 @@ run_wgetrc (const char *file)
}
xfree_null (com);
xfree_null (val);
- xfree (line);
++ln;
}
+ xfree (line);
fclose (fp);
return errcnt == 0;
diff --git a/src/netrc.c b/src/netrc.c
index 193d4f3..a31e079 100644
--- a/src/netrc.c
+++ b/src/netrc.c
@@ -164,48 +164,6 @@ search_netrc (const char *host, const char **acc, const char **passwd,
# define xrealloc realloc
-/* Read a line from FP. The function reallocs the storage as needed
- to accomodate for any length of the line. Reallocs are done
- storage exponentially, doubling the storage after each overflow to
- minimize the number of calls to realloc() and fgets(). The newline
- character at the end of line is retained.
-
- After end-of-file is encountered without anything being read, NULL
- is returned. NULL is also returned on error. To distinguish
- between these two cases, use the stdio function ferror(). */
-
-char *
-read_whole_line (FILE *fp)
-{
- int length = 0;
- int bufsize = 81;
- char *line = xmalloc (bufsize);
-
- while (fgets (line + length, bufsize - length, fp))
- {
- length += strlen (line + length);
- assert (length > 0);
- if (line[length - 1] == '\n')
- break;
- /* fgets() guarantees to read the whole line, or to use up the
- space we've given it. We can double the buffer
- unconditionally. */
- bufsize <<= 1;
- line = xrealloc (line, bufsize);
- }
- if (length == 0 || ferror (fp))
- {
- xfree (line);
- return NULL;
- }
- if (length + 1 < bufsize)
- /* Relieve the memory from our exponential greediness. We say
- `length + 1' because the terminating \0 is not included in
- LENGTH. We don't need to zero-terminate the string ourselves,
- though, because fgets() does that. */
- line = xrealloc (line, length + 1);
- return line;
-}
#endif /* STANDALONE */
/* Maybe add NEWENTRY to the account information list, LIST. NEWENTRY is
@@ -264,10 +222,11 @@ static acc_t *
parse_netrc (const char *path)
{
FILE *fp;
- char *line, *p, *tok;
+ char *line = NULL, *p, *tok;
const char *premature_token;
acc_t *current, *retval;
int ln, qmark;
+ size_t bufsize = 0;
/* The latest token we've seen in the file. */
enum
@@ -290,7 +249,7 @@ parse_netrc (const char *path)
premature_token = NULL;
/* While there are lines in the file... */
- while ((line = read_whole_line (fp)) != NULL)
+ while (getline (&line, &bufsize, fp) > 0)
{
ln ++;
@@ -423,10 +382,9 @@ parse_netrc (const char *path)
exec_name, path, ln, tok);
}
}
-
- xfree (line);
}
+ xfree (line);
fclose (fp);
/* Finalize the last machine entry we found. */
diff --git a/src/utils.c b/src/utils.c
index f7baed6..4db9374 100644
--- a/src/utils.c
+++ b/src/utils.c
@@ -1118,56 +1118,6 @@ has_html_suffix_p (const char *fname)
return false;
}
-/* Read a line from FP and return the pointer to freshly allocated
- storage. The storage space is obtained through malloc() and should
- be freed with free() when it is no longer needed.
-
- The length of the line is not limited, except by available memory.
- The newline character at the end of line is retained. The line is
- terminated with a zero character.
-
- After end-of-file is encountered without anything being read, NULL
- is returned. NULL is also returned on error. To distinguish
- between these two cases, use the stdio function ferror(). */
-
-char *
-read_whole_line (FILE *fp)
-{
- int length = 0;
- int bufsize = 82;
- char *line = xmalloc (bufsize);
-
- while (fgets (line + length, bufsize - length, fp))
- {
- length += strlen (line + length);
- if (length == 0)
- /* Possible for example when reading from a binary file where
- a line begins with \0. */
- continue;
-
- if (line[length - 1] == '\n')
- break;
-
- /* fgets() guarantees to read the whole line, or to use up the
- space we've given it. We can double the buffer
- unconditionally. */
- bufsize <<= 1;
- line = xrealloc (line, bufsize);
- }
- if (length == 0 || ferror (fp))
- {
- xfree (line);
- return NULL;
- }
- if (length + 1 < bufsize)
- /* Relieve the memory from our exponential greediness. We say
- `length + 1' because the terminating \0 is not included in
- LENGTH. We don't need to zero-terminate the string ourselves,
- though, because fgets() does that. */
- line = xrealloc (line, length + 1);
- return line;
-}
-
/* Read FILE into memory. A pointer to `struct file_memory' are
returned; use struct element `content' to access file contents, and
the element `length' to know the file length. `content' is *not*
diff --git a/src/utils.h b/src/utils.h
index 67d8d25..7c6f2ce 100644
--- a/src/utils.h
+++ b/src/utils.h
@@ -98,7 +98,6 @@ bool has_wildcards_p (const char *);
bool has_html_suffix_p (const char *);
-char *read_whole_line (FILE *);
struct file_memory *wget_read_file (const char *);
void wget_read_file_free (struct file_memory *);
--
1.7.10.4
