X-Git-Url: https://gitweb.ps.run/ps-cgit/blobdiff_plain/2101e26fd68f816e77de62b93df4c32fd1110d0c..6f9e8a9659996281248c9002497148d489003bce:/parsing.c

diff --git a/parsing.c b/parsing.c
index 6cab0e9..53c29bb 100644
--- a/parsing.c
+++ b/parsing.c
@@ -1,6 +1,6 @@
-/* config.c: parsing of config files
+/* parsing.c: parsing of config files
  *
- * Copyright (C) 2006 Lars Hjemli
+ * Copyright (C) 2006-2014 cgit Development Team <cgit@lists.zx2c4.com>
  *
  * Licensed under GNU General Public License v2
  *   (see COPYING for full license text)
@@ -8,152 +8,248 @@
 
 #include "cgit.h"
 
-int next_char(FILE *f)
+/*
+ * 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)
 {
-	int c = fgetc(f);
-	if (c=='\r') {
-		c = fgetc(f);
-		if (c!='\n') {
-			ungetc(c, f);
-			c = '\r';
+	char *c, *cmd, *p;
+	struct cgit_repo *repo;
+
+	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 = NULL;
+	c = strchr(url, '/');
+	while (c) {
+		c[0] = '\0';
+		repo = cgit_get_repoinfo(url);
+		if (repo) {
+			ctx.repo = repo;
+			cmd = c;
+		}
+		c[0] = '/';
+		c = strchr(c + 1, '/');
+	}
+
+	if (ctx.repo) {
+		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;
 	}
-	return c;
 }
 
-void skip_line(FILE *f)
+static char *substr(const char *head, const char *tail)
 {
-	int c;
+	char *buf;
 
-	while((c=next_char(f)) && c!='\n' && c!=EOF)
-		;
+	if (tail < head)
+		return xstrdup("");
+	buf = xmalloc(tail - head + 1);
+	strncpy(buf, head, tail - head);
+	buf[tail - head] = '\0';
+	return buf;
 }
 
-int read_config_line(FILE *f, char *line, const char **value, int bufsize)
+static const char *parse_user(const char *t, char **name, char **email, unsigned long *date)
 {
-	int i = 0, isname = 0;
-
-	*value = NULL;
-	while(i<bufsize-1) {
-		int c = next_char(f);
-		if (!isname && (c=='#' || c==';')) {
-			skip_line(f);
-			continue;
-		}
-		if (!isname && isspace(c))
-			continue;
-
-		if (c=='=' && !*value) {
-			line[i] = 0;
-			*value = &line[i+1];
-		} else if (c=='\n' && !isname) {
-			i = 0;
-			continue;
-		} else if (c=='\n' || c==EOF) {
-			line[i] = 0;
-			break;
-		} else {
-			line[i]=c;
-		}
-		isname = 1;
-		i++;
-	}
-	line[i+1] = 0;
-	return i;
-}
+	const char *line_end = strchrnul(t, '\n');
+	struct ident_split ident;
+	unsigned email_len;
 
-int cgit_read_config(const char *filename, configfn fn)
-{
-	int ret = 0, len;
-	char line[256];
-	const char *value;
-	FILE *f = fopen(filename, "r");
+	if (!split_ident_line(&ident, t, line_end - t)) {
+		*name = substr(ident.name_begin, ident.name_end);
 
-	if (!f)
-		return -1;
+		email_len = ident.mail_end - ident.mail_begin;
+		*email = xmalloc(strlen("<") + email_len + strlen(">") + 1);
+		sprintf(*email, "<%.*s>", email_len, ident.mail_begin);
 
-	while((len = read_config_line(f, line, &value, sizeof(line))) > 0)
-		(*fn)(line, value);
+		if (ident.date_begin)
+			*date = strtoul(ident.date_begin, NULL, 10);
+	}
 
-	fclose(f);
-	return ret;
+	if (*line_end)
+		return line_end + 1;
+	else
+		return line_end;
 }
 
-int cgit_parse_query(char *txt, configfn fn)
+#ifdef NO_ICONV
+#define reencode(a, b, c)
+#else
+static const char *reencode(char **txt, const char *src_enc, const char *dst_enc)
 {
-	char *t, *value = NULL, c;
+	char *tmp;
 
 	if (!txt)
-		return 0;
+		return NULL;
 
-	t = txt = xstrdup(txt);
- 
-	while((c=*t) != '\0') {
-		if (c=='=') {
-			*t = '\0';
-			value = t+1;
-		} else if (c=='&') {
-			*t = '\0';
-			(*fn)(txt, value);
-			txt = t+1;
-			value = NULL;
-		}
-		t++;
-	}
-	if (t!=txt)
-		(*fn)(txt, value);
-	return 0;
-}
+	if (!*txt || !src_enc || !dst_enc)
+		return *txt;
 
-char *substr(const char *head, const char *tail)
-{
-	char *buf;
+	/* no encoding needed if src_enc equals dst_enc */
+	if (!strcasecmp(src_enc, dst_enc))
+		return *txt;
 
-	buf = xmalloc(tail - head + 1);
-	strncpy(buf, head, tail - head);
-	buf[tail - head] = '\0';
-	return buf;
+	tmp = reencode_string(*txt, dst_enc, src_enc);
+	if (tmp) {
+		free(*txt);
+		*txt = tmp;
+	}
+	return *txt;
 }
+#endif
 
 struct commitinfo *cgit_parse_commit(struct commit *commit)
 {
 	struct commitinfo *ret;
-	char *p = commit->buffer, *t = commit->buffer;
+	const char *p = get_cached_commit_buffer(commit, NULL);
+	const char *t;
 
 	ret = xmalloc(sizeof(*ret));
 	ret->commit = commit;
-
-	if (strncmp(p, "tree ", 5))
+	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 (!starts_with(p, "tree "))
 		die("Bad commit: %s", sha1_to_hex(commit->object.sha1));
 	else
 		p += 46; // "tree " + hex[40] + "\n"
 
-	while (!strncmp(p, "parent ", 7))
+	while (starts_with(p, "parent "))
 		p += 48; // "parent " + hex[40] + "\n"
 
-	if (!strncmp(p, "author ", 7)) {
-		p += 7;
-		t = strchr(p, '<') - 1;
-		ret->author = substr(p, t);
-		p = strchr(p, '\n') + 1;
+	if (p && starts_with(p, "author ")) {
+		p = parse_user(p + 7, &ret->author, &ret->author_email,
+			&ret->author_date);
+	}
+
+	if (p && starts_with(p, "committer ")) {
+		p = parse_user(p + 10, &ret->committer, &ret->committer_email,
+			&ret->committer_date);
 	}
 
-	if (!strncmp(p, "committer ", 9)) {
+	if (p && starts_with(p, "encoding ")) {
 		p += 9;
-		t = strchr(p, '<') - 1;
-		ret->committer = substr(p, t);
-		p = strchr(p, '\n') + 1;
+		t = strchr(p, '\n');
+		if (t) {
+			ret->msg_encoding = substr(p, t + 1);
+			p = t + 1;
+		}
 	}
 
-	while (*p == '\n')
-		p = strchr(p, '\n') + 1;
+	/* if no special encoding is found, assume UTF-8 */
+	if (!ret->msg_encoding)
+		ret->msg_encoding = xstrdup("UTF-8");
+
+	// skip unknown header fields
+	while (p && *p && (*p != '\n')) {
+		p = strchr(p, '\n');
+		if (p)
+			p++;
+	}
+
+	// skip empty lines between headers and message
+	while (p && *p == '\n')
+		p++;
+
+	if (!p)
+		return ret;
 
 	t = strchr(p, '\n');
-	ret->subject = substr(p, t);
+	if (t) {
+		ret->subject = substr(p, t);
+		p = t + 1;
+
+		while (p && *p == '\n') {
+			p = strchr(p, '\n');
+			if (p)
+				p++;
+		}
+		if (p)
+			ret->msg = xstrdup(p);
+	} else
+		ret->subject = xstrdup(p);
+
+	reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->committer, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->committer_email, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->subject, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->msg, ret->msg_encoding, PAGE_ENCODING);
+
+	return ret;
+}
+
+
+struct taginfo *cgit_parse_tag(struct tag *tag)
+{
+	void *data;
+	enum object_type type;
+	unsigned long size;
+	const 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 (starts_with(p, "tagger ")) {
+			p = parse_user(p + 7, &ret->tagger, &ret->tagger_email,
+				&ret->tagger_date);
+		} else {
+			p = strchr(p, '\n');
+			if (p)
+				p++;
+		}
+	}
 
-	while (*p == '\n')
-		p = strchr(p, '\n') + 1;
-	ret->msg = p;
+	// skip empty lines between headers and message
+	while (p && *p == '\n')
+		p++;
 
+	if (p && *p)
+		ret->msg = xstrdup(p);
+	free(data);
 	return ret;
 }