Abstract out the "name <email> date" handling of commit-tree.c

We'll want to use it for the tagging too.

Makefile

@@ -58,7 +58,7 @@ install: $(PROG) $(SCRIPTS)
 
 LIB_OBJS=read-cache.o sha1_file.o usage.o object.o commit.o tree.o blob.o \
 	 tag.o date.o index.o diff-delta.o patch-delta.o entry.o path.o \
-	 epoch.o refs.o csum-file.o pack-check.o pkt-line.o connect.o
+	 epoch.o refs.o csum-file.o pack-check.o pkt-line.o connect.o ident.o
 LIB_FILE=libgit.a
 LIB_H=cache.h object.h blob.h tree.h commit.h tag.h delta.h epoch.h csum-file.h \
 	pack.h pkt-line.h refs.h

cache.h

@@ -211,6 +211,9 @@ const char *show_date(unsigned long time, int timezone);
 void parse_date(const char *date, char *buf, int bufsize);
 void datestamp(char *buf, int bufsize);
 
+extern int setup_ident(void);
+extern char *get_ident(const char *name, const char *email, const char *date_str);
+
 static inline void *xmalloc(size_t size)
 {
 	void *ret = malloc(size);

commit-tree.c

@@ -45,39 +45,6 @@ static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...)
 	memcpy(buf + size, one_line, len);
 }
 
-static void remove_special(char *p)
-{
-	char c;
-	char *dst = p, *src = p;
-
-	for (;;) {
-		c = *src;
-		src++;
-		switch(c) {
-		case '\n': case '<': case '>':
-			continue;
-		}
-		*dst++ = c;
-		if (!c)
-			break;
-	}
-
-	/*
-	 * Go back, and remove crud from the end: some people
-	 * have commas etc in their gecos field
-	 */
-	dst--;
-	while (--dst >= p) {
-		unsigned char c = *dst;
-		switch (c) {
-		case ',': case ';': case '.':
-			*dst = 0;
-			continue;
-		}
-		break;
-	}
-}
-
 static void check_valid(unsigned char *sha1, const char *expect)
 {
 	void *buf;
@@ -112,18 +79,23 @@ static int new_parent(int idx)
 	return 1;
 }
 
+static char *git_author_info(void)
+{
+	return get_ident(gitenv("GIT_AUTHOR_NAME"), gitenv("GIT_AUTHOR_EMAIL"), gitenv("GIT_AUTHOR_DATE"));
+}
+
+static char *git_committer_info(void)
+{
+	return get_ident(gitenv("GIT_COMMITTER_NAME"), gitenv("GIT_COMMITTER_EMAIL"), gitenv("GIT_COMMITTER_DATE"));
+}
+
 int main(int argc, char **argv)
 {
-	int i, len;
+	int i;
 	int parents = 0;
 	unsigned char tree_sha1[20];
 	unsigned char commit_sha1[20];
-	char *gecos, *realgecos, *commitgecos;
-	char *email, *commitemail, realemail[1000];
-	char date[50], realdate[50];
-	char *audate, *cmdate;
 	char comment[1000];
-	struct passwd *pw;
 	char *buffer;
 	unsigned int size;
 
@@ -142,35 +114,7 @@ int main(int argc, char **argv)
 	}
 	if (!parents)
 		fprintf(stderr, "Committing initial tree %s\n", argv[1]);
-	pw = getpwuid(getuid());
+	setup_ident();
-	if (!pw)
-		die("You don't exist. Go away!");
-	realgecos = pw->pw_gecos;
-	len = strlen(pw->pw_name);
-	memcpy(realemail, pw->pw_name, len);
-	realemail[len] = '@';
-	gethostname(realemail+len+1, sizeof(realemail)-len-1);
-	if (!strchr(realemail+len+1, '.')) {
-		strcat(realemail, ".");
-		getdomainname(realemail+strlen(realemail), sizeof(realemail)-strlen(realemail)-1);
-	}
-
-	datestamp(realdate, sizeof(realdate));
-	strcpy(date, realdate);
-
-	commitgecos = gitenv("GIT_COMMITTER_NAME") ? : realgecos;
-	commitemail = gitenv("GIT_COMMITTER_EMAIL") ? : realemail;
-	gecos = gitenv("GIT_AUTHOR_NAME") ? : realgecos;
-	email = gitenv("GIT_AUTHOR_EMAIL") ? : realemail;
-	audate = gitenv("GIT_AUTHOR_DATE");
-	if (audate)
-		parse_date(audate, date, sizeof(date));
-	cmdate = gitenv("GIT_COMMITTER_DATE");
-	if (cmdate)
-		parse_date(cmdate, realdate, sizeof(realdate));
-
-	remove_special(gecos); remove_special(realgecos); remove_special(commitgecos);
-	remove_special(email); remove_special(realemail); remove_special(commitemail);
 
 	init_buffer(&buffer, &size);
 	add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1));
@@ -184,8 +128,8 @@ int main(int argc, char **argv)
 		add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i]));
 
 	/* Person/date information */
-	add_buffer(&buffer, &size, "author %s <%s> %s\n", gecos, email, date);
+	add_buffer(&buffer, &size, "author %s\n", git_author_info());
-	add_buffer(&buffer, &size, "committer %s <%s> %s\n\n", commitgecos, commitemail, realdate);
+	add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info());
 
 	/* And add the comment */
 	while (fgets(comment, sizeof(comment), stdin) != NULL)

ident.c

@@ -0,0 +1,138 @@
+/*
+ * ident.c
+ *
+ * create git identifier lines of the form "name <email> date"
+ *
+ * Copyright (C) 2005 Linus Torvalds
+ */
+#include "cache.h"
+
+#include <pwd.h>
+#include <time.h>
+#include <ctype.h>
+
+static char real_email[1000];
+static char real_name[1000];
+static char real_date[50];
+
+int setup_ident(void)
+{
+	int len;
+	struct passwd *pw = getpwuid(getuid());
+
+	if (!pw)
+		die("You don't exist. Go away!");
+
+	/* Get the name ("gecos") */
+	len = strlen(pw->pw_gecos);
+	if (len >= sizeof(real_name))
+		die("Your parents must have hated you");
+	memcpy(real_name, pw->pw_gecos, len+1);
+
+	/* Make up a fake email address (name + '@' + hostname [+ '.' + domainname]) */
+	len = strlen(pw->pw_name);
+	if (len > sizeof(real_email)/2)
+		die("Your parents must have hated you");
+	memcpy(real_email, pw->pw_name, len);
+	real_email[len++] = '@';
+	gethostname(real_email + len, sizeof(real_email) - len);
+	if (!strchr(real_email+len, '.')) {
+		len = strlen(real_email);
+		real_email[len++] = '.';
+		getdomainname(real_email+len, sizeof(real_email)-len);
+	}
+
+	/* And set the default date */
+	datestamp(real_date, sizeof(real_date));
+	return 0;
+}
+
+static int add_raw(char *buf, int size, int offset, const char *str)
+{
+	int len = strlen(str);
+	if (offset + len > size)
+		return size;
+	memcpy(buf + offset, str, len);
+	return offset + len;
+}
+
+static int crud(unsigned char c)
+{
+	static const char crud_array[256] = {
+		[0 ... 31] = 1,
+		[' '] = 1,
+		['.'] = 1, [','] = 1,
+		[':'] = 1, [';'] = 1,
+		['<'] = 1, ['>'] = 1,
+		['"'] = 1, ['\''] = 1,
+	};
+	return crud_array[c];
+}
+
+/*
+ * Copy over a string to the destination, but avoid special
+ * characters ('\n', '<' and '>') and remove crud at the end
+ */
+static int copy(char *buf, int size, int offset, const char *src)
+{
+	int i, len;
+	unsigned char c;
+
+	/* Remove crud from the beginning.. */
+	while ((c = *src) != 0) {
+		if (!crud(c))
+			break;
+		src++;
+	}
+
+	/* Remove crud from the end.. */
+	len = strlen(src);
+	while (len > 0) {
+		c = src[len-1];
+		if (!crud(c))
+			break;
+		--len;
+	}
+
+	/*
+	 * Copy the rest to the buffer, but avoid the special
+	 * characters '\n' '<' and '>' that act as delimeters on
+	 * a identification line
+	 */
+	for (i = 0; i < len; i++) {
+		c = *src++;
+		switch (c) {
+		case '\n': case '<': case '>':
+			continue;
+		}
+		if (offset >= size)
+			return size;
+		buf[offset++] = c;
+	}
+	return offset;
+}
+
+char *get_ident(const char *name, const char *email, const char *date_str)
+{
+	static char buffer[1000];
+	char date[50];
+	int i;
+
+	if (!name)
+		name = real_name;
+	if (!email)
+		email = real_email;
+	strcpy(date, real_date);
+	if (date_str)
+		parse_date(date_str, date, sizeof(date));
+
+	i = copy(buffer, sizeof(buffer), 0, name);
+	i = add_raw(buffer, sizeof(buffer), i, " <");
+	i = copy(buffer, sizeof(buffer), i, email);
+	i = add_raw(buffer, sizeof(buffer), i, "> ");
+	i = copy(buffer, sizeof(buffer), i, date);
+	if (i >= sizeof(buffer))
+		die("Impossibly long personal identifier");
+	buffer[i] = 0;
+	return buffer;
+}