summary refs log tree commit diff
path: root/bin/htagml.c
diff options
context:
space:
mode:
Diffstat (limited to 'bin/htagml.c')
-rw-r--r--bin/htagml.c134
1 files changed, 55 insertions, 79 deletions
diff --git a/bin/htagml.c b/bin/htagml.c
index 8cc2272c..d8825a65 100644
--- a/bin/htagml.c
+++ b/bin/htagml.c
@@ -24,23 +24,6 @@
 #include <sysexits.h>
 #include <unistd.h>
 
-struct Tag {
-	char *tag;
-	regex_t regex;
-};
-
-struct Match {
-	struct Tag *tag;
-	regmatch_t match;
-};
-
-static int compar(const void *_a, const void *_b) {
-	const struct Match *a = _a;
-	const struct Match *b = _b;
-	return (a->match.rm_so > b->match.rm_so)
-		- (a->match.rm_so < b->match.rm_so);
-}
-
 static char *nomagic(const char *pattern) {
 	char *buf = malloc(2 * strlen(pattern) + 1);
 	if (!buf) err(EX_OSERR, "malloc");
@@ -83,7 +66,11 @@ int main(int argc, char *argv[]) {
 
 	size_t len = 0;
 	size_t cap = 256;
-	struct Tag *tags = malloc(cap * sizeof(*tags));
+	struct Tag {
+		char *tag;
+		int num;
+		regex_t regex;
+	} *tags = malloc(cap * sizeof(*tags));
 	if (!tags) err(EX_OSERR, "malloc");
 
 	char *buf = NULL;
@@ -92,14 +79,8 @@ int main(int argc, char *argv[]) {
 		char *line = buf;
 		char *tag = strsep(&line, "\t");
 		char *file = strsep(&line, "\t");
-		char *search = strsep(&line, "\n");
-		if (!tag || !file || !search) errx(EX_DATAERR, "malformed tags file");
-		if (search[0] != '/' || search[strlen(search)-1] != '/') {
-			warnx("tag %s definition is not a forward search: %s", tag, search);
-			continue;
-		}
-		search++;
-		search[strlen(search)-1] = '\0';
+		char *def = strsep(&line, "\n");
+		if (!tag || !file || !def) errx(EX_DATAERR, "malformed tags file");
 
 		if (strcmp(file, name)) continue;
 		if (len == cap) {
@@ -108,76 +89,71 @@ int main(int argc, char *argv[]) {
 		}
 		tags[len].tag = strdup(tag);
 		if (!tags[len].tag) err(EX_OSERR, "strdup");
-		char *pattern = nomagic(search);
-		int error = regcomp(&tags[len].regex, pattern, REG_NEWLINE);
-		if (error) errx(EX_DATAERR, "invalid regex: %s", pattern);
-		free(pattern);
+
+		tags[len].num = 0;
+		if (def[0] == '/' || def[0] == '?') {
+			def++;
+			def[strlen(def)-1] = '\0';
+			char *search = nomagic(def);
+			int error = regcomp(
+				&tags[len].regex, search, REG_NEWLINE | REG_NOSUB
+			);
+			free(search);
+			if (error) {
+				warnx("invalid regex for tag %s: %s", tag, def);
+				continue;
+			}
+		} else {
+			tags[len].num = strtol(def, &def, 10);
+			if (*def) {
+				warnx("invalid line number for tag %s: %s", tag, def);
+				continue;
+			}
+		}
 		len++;
 	}
-	free(buf);
 	fclose(file);
 
 	file = fopen(name, "r");
 	if (!file) err(EX_NOINPUT, "%s", name);
 
-	struct stat stat;
-	int error = fstat(fileno(file), &stat);
-	if (error) err(EX_IOERR, "%s", name);
-	buf = malloc(stat.st_size + 1);
-	if (!buf) err(EX_OSERR, "malloc");
-
-	size_t size = fread(buf, 1, stat.st_size, file);
-	if (size < (size_t)stat.st_size && ferror(file)) err(EX_IOERR, "%s", name);
-	buf[size] = '\0';
-	fclose(file);
-
-	struct Match *matches = calloc(len, sizeof(*matches));
-	if (!matches) err(EX_OSERR, "calloc");
-	for (size_t i = 0; i < len; ++i) {
-		matches[i].tag = &tags[i];
-		regexec(&tags[i].regex, buf, 1, &matches[i].match, 0);
-	}
-	qsort(matches, len, sizeof(*matches), compar);
-
-	char *main;
-	const char *base = strrchr(name, '/');
-	int n = asprintf(&main, "M%s", (base ? &base[1] : name));
-	if (n < 0) err(EX_OSERR, "asprintf");
-	if (strrchr(main, '.')) *strrchr(main, '.') = '\0';
-
-	regoff_t pos = 0;
+	int num = 0;
 	if (pre) printf("<pre>");
-	for (size_t i = 0; i < len; ++i) {
-		if (matches[i].match.rm_so == matches[i].match.rm_eo) {
-			warnx("no match for tag %s", matches[i].tag->tag);
-			continue;
+	while (0 < getline(&buf, &bufCap, file) && ++num) {
+		struct Tag *tag = NULL;
+		for (size_t i = 0; i < len; ++i) {
+			if (tags[i].num) {
+				if (num != tags[i].num) continue;
+			} else {
+				if (regexec(&tags[i].regex, buf, 0, NULL, 0)) continue;
+			}
+			tag = &tags[i];
+			break;
 		}
-		if (matches[i].match.rm_so <= pos) {
-			warnx("overlapping match for tag %s", matches[i].tag->tag);
+		if (!tag) {
+			escape(buf, strlen(buf));
 			continue;
 		}
 
-		pos += escape(&buf[pos], matches[i].match.rm_so - pos);
-		const char *text = matches[i].tag->tag;
-		if (!strcmp(text, main)) text = "main";
-		if (!strcmp(text, "yyparse") || !strcmp(text, "yylex")) text = "%%";
-		char *tag = strstr(&buf[pos], text);
-		if (!tag || tag >= &buf[matches[i].match.rm_eo]) {
-			warnx("tag %s does not occur in match", matches[i].tag->tag);
-			continue;
+		char *text = tag->tag;
+		char *match = strstr(buf, text);
+		if (!match && tag->tag[0] == 'M') {
+			text = "main";
+			match = strstr(buf, text);
 		}
-
-		pos += escape(&buf[pos], tag - &buf[pos]);
+		if (match) escape(buf, match - buf);
 		printf("<a class=\"tag\" id=\"");
-		escape(matches[i].tag->tag, strlen(matches[i].tag->tag));
+		escape(tag->tag, strlen(tag->tag));
 		printf("\" href=\"#");
-		escape(matches[i].tag->tag, strlen(matches[i].tag->tag));
+		escape(tag->tag, strlen(tag->tag));
 		printf("\">");
-		pos += escape(&buf[pos], strlen(text));
+		if (match) {
+			match += escape(match, strlen(text));
+		} else {
+			escape(buf, strlen(buf));
+		}
 		printf("</a>");
-
-		pos += escape(&buf[pos], matches[i].match.rm_eo - pos);
+		if (match) escape(match, strlen(match));
 	}
-	escape(&buf[pos], strlen(&buf[pos]));
 	if (pre) printf("</pre>");
 }
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-05-08 18:15:28 +0000
many lines that do not connect with any commits we're actually showing. We also teach the "diff" and "commit" UIs to respect the follow flag on URLs, causing the single-file version of these UIs to detect renames. This feature is needed only for commits that rename the path we're interested in. For commits before the file has been renamed (i.e. that appear later in the log list) we change the file path in the links from the log to point to the old name; this means that links to commits always limit by the path known to that commit. If we didn't do this we would need to walk down the log diff'ing every commit whenever we want to show a commit. The drawback is that the "Log" link in the top bar of such a page links to the log limited by the old name, so it will only show pre-rename commits. I consider this a reasonable trade-off since the "Back" button still works and the log matches the path displayed in the top bar. Since following renames requires running diff on every commit we consider, I've added a knob to the configuration file to globally enable/disable this feature. Note that we may consider a large number of commits the revision walking machinery no longer performs any path limitation so we have to examine every commit until we find a page full of commits that affect the target path or something related to it. Suggested-by: René Neumann <necoro@necoro.eu> Signed-off-by: John Keeping <john@keeping.me.uk> 2015-08-12shared: make cgit_diff_tree_cb publicJohn Keeping This will allow us to use this nice wrapper function elsewhere, avoiding dealing with the diff queue when we only need to inspect a filepair. Signed-off-by: John Keeping <john@keeping.me.uk> 2015-08-12t0110: Chain together using &&Jason A. Donenfeld 2015-08-12about: always ensure page has a trailing slashJason A. Donenfeld Otherwise we can't easily embed links to other /about/ pages. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> 2015-08-12filters: apply HTML escapingLazaros Koromilas http://www.w3.org/International/questions/qa-escapes#use 2015-08-12git: update to v2.5.0Christian Hesse Update to git version v2.5.0. * Upstream commit 5455ee0573a22bb793a7083d593ae1ace909cd4c (Merge branch 'bc/object-id') changed API: for_each_ref() callback functions were taught to name the objects not with "unsigned char sha1[20]" but with "struct object_id". * Upstream commit dcf692625ac569fefbe52269061230f4fde10e47 (path.c: make get_pathname() call sites return const char *) Signed-off-by: Christian Hesse <mail@eworm.de> 2015-08-12Fix processing of repo.hide and repo.ignoreDaniel Reichelt