parsing.c: be prepared for unexpected content in commit/tag objects

When parsing commits and tags cgit made too many assumptions about the
formatting of said objects. This patch tries to make the code be more
prepared to handle 'malformed' objects.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>

2 files changed, 97 insertions, 64 deletions

diff --git a/cgit.h b/cgit.h
index 1615616..08fd95a 100644
--- a/cgit.h
+++ b/cgit.h
@@ -1,241 +1,241 @@
 #ifndef CGIT_H
 #define CGIT_H
 
 
 #include <git-compat-util.h>
 #include <cache.h>
 #include <grep.h>
 #include <object.h>
 #include <tree.h>
 #include <commit.h>
 #include <tag.h>
 #include <diff.h>
 #include <diffcore.h>
 #include <refs.h>
 #include <revision.h>
 #include <log-tree.h>
 #include <archive.h>
 #include <xdiff/xdiff.h>
 #include <utf8.h>
 
 
 /*
  * Dateformats used on misc. pages
  */
 #define FMT_LONGDATE "%Y-%m-%d %H:%M:%S (%Z)"
 #define FMT_SHORTDATE "%Y-%m-%d"
 #define FMT_ATOMDATE "%Y-%m-%dT%H:%M:%SZ"
 
 
 /*
  * Limits used for relative dates
  */
 #define TM_MIN    60
 #define TM_HOUR  (TM_MIN * 60)
 #define TM_DAY   (TM_HOUR * 24)
 #define TM_WEEK  (TM_DAY * 7)
 #define TM_YEAR  (TM_DAY * 365)
 #define TM_MONTH (TM_YEAR / 12.0)
 
 
 /*
  * Default encoding
  */
 #define PAGE_ENCODING "UTF-8"
 
 typedef void (*configfn)(const char *name, const char *value);
 typedef void (*filepair_fn)(struct diff_filepair *pair);
 typedef void (*linediff_fn)(char *line, int len);
 
 struct cgit_repo {
 	char *url;
 	char *name;
 	char *path;
 	char *desc;
 	char *owner;
 	char *defbranch;
 	char *group;
 	char *module_link;
 	char *readme;
 	char *clone_url;
 	int snapshots;
 	int enable_log_filecount;
 	int enable_log_linecount;
 };
 
 struct cgit_repolist {
 	int length;
 	int count;
 	struct cgit_repo *repos;
 };
 
 struct commitinfo {
 	struct commit *commit;
 	char *author;
 	char *author_email;
 	unsigned long author_date;
 	char *committer;
 	char *committer_email;
 	unsigned long committer_date;
 	char *subject;
 	char *msg;
 	char *msg_encoding;
 };
 
 struct taginfo {
 	char *tagger;
 	char *tagger_email;
-	int tagger_date;
+	unsigned long tagger_date;
 	char *msg;
 };
 
 struct refinfo {
 	const char *refname;
 	struct object *object;
 	union {
 		struct taginfo *tag;
 		struct commitinfo *commit;
 	};
 };
 
 struct reflist {
 	struct refinfo **refs;
 	int alloc;
 	int count;
 };
 
 struct cgit_query {
 	int has_symref;
 	int has_sha1;
 	char *raw;
 	char *repo;
 	char *page;
 	char *search;
 	char *grep;
 	char *head;
 	char *sha1;
 	char *sha2;
 	char *path;
 	char *name;
 	char *mimetype;
 	int   ofs;
 };
 
 struct cgit_config {
 	char *agefile;
 	char *cache_root;
 	char *clone_prefix;
 	char *css;
 	char *favicon;
 	char *footer;
 	char *index_header;
 	char *index_info;
 	char *logo;
 	char *logo_link;
 	char *module_link;
 	char *repo_group;
 	char *robots;
 	char *root_title;
 	char *root_desc;
 	char *root_readme;
 	char *script_name;
 	char *virtual_root;
 	int cache_size;
 	int cache_dynamic_ttl;
 	int cache_max_create_time;
 	int cache_repo_ttl;
 	int cache_root_ttl;
 	int cache_static_ttl;
 	int enable_index_links;
 	int enable_log_filecount;
 	int enable_log_linecount;
 	int local_time;
 	int max_repo_count;
 	int max_commit_count;
 	int max_lock_attempts;
 	int max_msg_len;
 	int max_repodesc_len;
 	int nocache;
 	int renamelimit;
 	int snapshots;
 	int summary_branches;
 	int summary_log;
 	int summary_tags;
 };
 
 struct cgit_page {
 	time_t modified;
 	time_t expires;
 	size_t size;
 	char *mimetype;
 	char *charset;
 	char *filename;
 	char *title;
 };
 
 struct cgit_context {
 	struct cgit_query qry;
 	struct cgit_config cfg;
 	struct cgit_repo *repo;
 	struct cgit_page page;
 };
 
 struct cgit_snapshot_format {
 	const char *suffix;
 	const char *mimetype;
 	write_archive_fn_t write_func;
 	int bit;
 };
 
 extern const char *cgit_version;
 
 extern struct cgit_repolist cgit_repolist;
 extern struct cgit_context ctx;
 extern const struct cgit_snapshot_format cgit_snapshot_formats[];
 
 extern struct cgit_repo *cgit_add_repo(const char *url);
 extern struct cgit_repo *cgit_get_repoinfo(const char *url);
 extern void cgit_repo_config_cb(const char *name, const char *value);
 
 extern int chk_zero(int result, char *msg);
 extern int chk_positive(int result, char *msg);
 extern int chk_non_negative(int result, char *msg);
 
 extern char *trim_end(const char *str, char c);
 extern char *strlpart(char *txt, int maxlen);
 extern char *strrpart(char *txt, int maxlen);
 
 extern void cgit_add_ref(struct reflist *list, struct refinfo *ref);
 extern int cgit_refs_cb(const char *refname, const unsigned char *sha1,
 			int flags, void *cb_data);
 
 extern void *cgit_free_commitinfo(struct commitinfo *info);
 
 extern int cgit_diff_files(const unsigned char *old_sha1,
 			   const unsigned char *new_sha1,
 			   linediff_fn fn);
 
 extern void cgit_diff_tree(const unsigned char *old_sha1,
 			   const unsigned char *new_sha1,
 			   filepair_fn fn, const char *prefix);
 
 extern void cgit_diff_commit(struct commit *commit, filepair_fn fn);
 
 extern char *fmt(const char *format,...);
 
 extern struct commitinfo *cgit_parse_commit(struct commit *commit);
 extern struct taginfo *cgit_parse_tag(struct tag *tag);
 extern void cgit_parse_url(const char *url);
 
 extern const char *cgit_repobasename(const char *reponame);
 
 extern int cgit_parse_snapshots_mask(const char *str);
 
 /* libgit.a either links against or compiles its own implementation of
  * strcasestr(), and we'd like to reuse it. Simply re-declaring it
  * seems to do the trick.
  */
 extern char *strcasestr(const char *haystack, const char *needle);
 
 
 #endif /* CGIT_H */
diff --git a/parsing.c b/parsing.c
index 66e8b3d..c8f3048 100644
--- a/parsing.c
+++ b/parsing.c
@@ -1,208 +1,241 @@
 /* config.c: parsing of config files
  *
  * Copyright (C) 2006 Lars Hjemli
  *
  * Licensed under GNU General Public License v2
  *   (see COPYING for full license text)
  */
 
 #include "cgit.h"
 
 /*
  * url syntax: [repo ['/' cmd [ '/' path]]]
  *   repo: any valid repo url, may contain '/'
  *   cmd:  log | commit | diff | tree | view | blob | snapshot
  *   path: any valid path, may contain '/'
  *
  */
 void cgit_parse_url(const char *url)
 {
 	char *cmd, *p;
 
 	ctx.repo = NULL;
 	if (!url || url[0] == '\0')
 		return;
 
 	ctx.repo = cgit_get_repoinfo(url);
 	if (ctx.repo) {
 		ctx.qry.repo = ctx.repo->url;
 		return;
 	}
 
 	cmd = strchr(url, '/');
 	while (!ctx.repo && cmd) {
 		cmd[0] = '\0';
 		ctx.repo = cgit_get_repoinfo(url);
 		if (ctx.repo == NULL) {
 			cmd[0] = '/';
 			cmd = strchr(cmd + 1, '/');
 			continue;
 		}
 
 		ctx.qry.repo = ctx.repo->url;
 		p = strchr(cmd + 1, '/');
 		if (p) {
 			p[0] = '\0';
 			if (p[1])
 				ctx.qry.path = trim_end(p + 1, '/');
 		}
 		if (cmd[1])
 			ctx.qry.page = xstrdup(cmd + 1);
 		return;
 	}
 }
 
 char *substr(const char *head, const char *tail)
 {
 	char *buf;
 
 	buf = xmalloc(tail - head + 1);
 	strncpy(buf, head, tail - head);
 	buf[tail - head] = '\0';
 	return buf;
 }
 
+char *parse_user(char *t, char **name, char **email, unsigned long *date)
+{
+	char *p = t;
+	int mode = 1;
+
+	while (p && *p) {
+		if (mode == 1 && *p == '<') {
+			*name = substr(t, p - 1);
+			t = p;
+			mode++;
+		} else if (mode == 1 && *p == '\n') {
+			*name = substr(t, p);
+			p++;
+			break;
+		} else if (mode == 2 && *p == '>') {
+			*email = substr(t, p + 1);
+			t = p;
+			mode++;
+		} else if (mode == 2 && *p == '\n') {
+			*email = substr(t, p);
+			p++;
+			break;
+		} else if (mode == 3 && isdigit(*p)) {
+			*date = atol(p);
+			mode++;
+		} else if (*p == '\n') {
+			p++;
+			break;
+		}
+		p++;
+	}
+	return p;
+}
+
+const char *reencode(char **txt, const char *src_enc, const char *dst_enc)
+{
+	char *tmp;
+
+	if (!txt || !*txt || !src_enc || !dst_enc)
+		return *txt;
+
+	tmp = reencode_string(*txt, src_enc, dst_enc);
+	if (tmp) {
+		free(*txt);
+		*txt = tmp;
+	}
+	return *txt;
+}
+
 struct commitinfo *cgit_parse_commit(struct commit *commit)
 {
 	struct commitinfo *ret;
 	char *p = commit->buffer, *t = commit->buffer;
 
 	ret = xmalloc(sizeof(*ret));
 	ret->commit = commit;
 	ret->author = NULL;
 	ret->author_email = NULL;
 	ret->committer = NULL;
 	ret->committer_email = NULL;
 	ret->subject = NULL;
 	ret->msg = NULL;
 	ret->msg_encoding = NULL;
 
 	if (p == NULL)
 		return ret;
 
 	if (strncmp(p, "tree ", 5))
 		die("Bad commit: %s", sha1_to_hex(commit->object.sha1));
 	else
 		p += 46; // "tree " + hex[40] + "\n"
 
 	while (!strncmp(p, "parent ", 7))
 		p += 48; // "parent " + hex[40] + "\n"
 
-	if (!strncmp(p, "author ", 7)) {
-		p += 7;
-		t = strchr(p, '<') - 1;
-		ret->author = substr(p, t);
-		p = t;
-		t = strchr(t, '>') + 1;
-		ret->author_email = substr(p, t);
-		ret->author_date = atol(t+1);
-		p = strchr(t, '\n') + 1;
+	if (p && !strncmp(p, "author ", 7)) {
+		p = parse_user(p + 7, &ret->author, &ret->author_email,
+			&ret->author_date);
 	}
 
-	if (!strncmp(p, "committer ", 9)) {
-		p += 9;
-		t = strchr(p, '<') - 1;
-		ret->committer = substr(p, t);
-		p = t;
-		t = strchr(t, '>') + 1;
-		ret->committer_email = substr(p, t);
-		ret->committer_date = atol(t+1);
-		p = strchr(t, '\n') + 1;
+	if (p && !strncmp(p, "committer ", 9)) {
+		p = parse_user(p + 9, &ret->committer, &ret->committer_email,
+			&ret->committer_date);
 	}
 
-	if (!strncmp(p, "encoding ", 9)) {
+	if (p && !strncmp(p, "encoding ", 9)) {
 		p += 9;
-		t = strchr(p, '\n') + 1;
-		ret->msg_encoding = substr(p, t);
-		p = t;
-	} else
-		ret->msg_encoding = xstrdup(PAGE_ENCODING);
+		t = strchr(p, '\n');
+		if (t) {
+			ret->msg_encoding = substr(p, t + 1);
+			p = t + 1;
+		}
+	}
 
-	while (*p && (*p != '\n'))
-		p = strchr(p, '\n') + 1; // skip unknown header fields
+	// skip unknown header fields
+	while (p && *p && (*p != '\n')) {
+		p = strchr(p, '\n');
+		if (p)
+			p++;
+	}
 
-	while (*p == '\n')
-		p = strchr(p, '\n') + 1;
+	// skip empty lines between headers and message
+	while (p && *p == '\n')
+		p++;
+
+	if (!p)
+		return ret;
 
 	t = strchr(p, '\n');
 	if (t) {
-		if (*t == '\0')
-			ret->subject = "** empty **";
-		else
-			ret->subject = substr(p, t);
+		ret->subject = substr(p, t);
 		p = t + 1;
 
-		while (*p == '\n')
-			p = strchr(p, '\n') + 1;
-		ret->msg = xstrdup(p);
-	} else
-		ret->subject = substr(p, p+strlen(p));
-
-	if(strcmp(ret->msg_encoding, PAGE_ENCODING)) {
-		t = reencode_string(ret->subject, PAGE_ENCODING,
-				    ret->msg_encoding);
-		if(t) {
-			free(ret->subject);
-			ret->subject = t;
+		while (p && *p == '\n') {
+			p = strchr(p, '\n');
+			if (p)
+				p++;
 		}
+		if (p)
+			ret->msg = xstrdup(p);
+	} else
+		ret->subject = xstrdup(p);
 
-		t = reencode_string(ret->msg, PAGE_ENCODING,
-				    ret->msg_encoding);
-		if(t) {
-			free(ret->msg);
-			ret->msg = t;
-		}
+	if (ret->msg_encoding) {
+		reencode(&ret->subject, PAGE_ENCODING, ret->msg_encoding);
+		reencode(&ret->msg, PAGE_ENCODING, ret->msg_encoding);
 	}
 
 	return ret;
 }
 
 
 struct taginfo *cgit_parse_tag(struct tag *tag)
 {
 	void *data;
 	enum object_type type;
 	unsigned long size;
-	char *p, *t;
+	char *p;
 	struct taginfo *ret;
 
 	data = read_sha1_file(tag->object.sha1, &type, &size);
 	if (!data || type != OBJ_TAG) {
 		free(data);
 		return 0;
 	}
 
 	ret = xmalloc(sizeof(*ret));
 	ret->tagger = NULL;
 	ret->tagger_email = NULL;
 	ret->tagger_date = 0;
 	ret->msg = NULL;
 
 	p = data;
 
 	while (p && *p) {
 		if (*p == '\n')
 			break;
 
 		if (!strncmp(p, "tagger ", 7)) {
-			p += 7;
-			t = strchr(p, '<') - 1;
-			ret->tagger = substr(p, t);
-			p = t;
-			t = strchr(t, '>') + 1;
-			ret->tagger_email = substr(p, t);
-			ret->tagger_date = atol(t+1);
+			p = parse_user(p + 7, &ret->tagger, &ret->tagger_email,
+				&ret->tagger_date);
+		} else {
+			p = strchr(p, '\n');
+			if (p)
+				p++;
 		}
-		p = strchr(p, '\n') + 1;
 	}
 
-	while (p && *p && (*p != '\n'))
-		p = strchr(p, '\n') + 1; // skip unknown tag fields
+	// skip empty lines between headers and message
+	while (p && *p == '\n')
+		p++;
 
-	while (p && (*p == '\n'))
-		p = strchr(p, '\n') + 1;
 	if (p && *p)
 		ret->msg = xstrdup(p);
 	free(data);
 	return ret;
 }