string_list: add two new functions for splitting strings

Add two new functions, string_list_split() and
string_list_split_in_place().  These split a string into a string_list
on a separator character.  The first makes copies of the substrings
(leaving the input string untouched) and the second splits the
original string in place, overwriting the separator characters with
NULs and referring to the original string's memory.

These functions are similar to the strbuf_split_*() functions except
that they work with the more powerful string_list interface.

Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

.gitignore

@@ -193,6 +193,7 @@
 /test-run-command
 /test-sha1
 /test-sigchain
+/test-string-list
 /test-subprocess
 /test-svn-fe
 /common-cmds.h

Documentation/technical/api-string-list.txt

@@ -21,7 +21,8 @@ member (you need this if you add things later) and you should set the
 `nr` and `alloc` members in that case, too.
 
 . Adds new items to the list, using `string_list_append`,
-  `string_list_append_nodup`, or `string_list_insert`.
+  `string_list_append_nodup`, `string_list_insert`,
+  `string_list_split`, and/or `string_list_split_in_place`.
 
 . Can check if a string is in the list using `string_list_has_string` or
   `unsorted_string_list_has_string` and get it from the list using
@@ -135,6 +136,25 @@ counterpart for sorted lists, which performs a binary search.
 	is set. The third parameter controls if the `util` pointer of the
 	items should be freed or not.
 
+`string_list_split`::
+`string_list_split_in_place`::
+
+	Split a string into substrings on a delimiter character and
+	append the substrings to a `string_list`.  If `maxsplit` is
+	non-negative, then split at most `maxsplit` times.  Return the
+	number of substrings appended to the list.
++
+`string_list_split` requires a `string_list` that has `strdup_strings`
+set to true; it leaves the input string untouched and makes copies of
+the substrings in newly-allocated memory.
+`string_list_split_in_place` requires a `string_list` that has
+`strdup_strings` set to false; it splits the input string in place,
+overwriting the delimiter characters with NULs and creating new
+string_list_items that point into the original string (the original
+string must therefore not be modified or freed while the `string_list`
+is in use).
+
+
 Data structures
 ---------------
 

Makefile

@@ -501,6 +501,7 @@ TEST_PROGRAMS_NEED_X += test-run-command
 TEST_PROGRAMS_NEED_X += test-scrap-cache-tree
 TEST_PROGRAMS_NEED_X += test-sha1
 TEST_PROGRAMS_NEED_X += test-sigchain
+TEST_PROGRAMS_NEED_X += test-string-list
 TEST_PROGRAMS_NEED_X += test-subprocess
 TEST_PROGRAMS_NEED_X += test-svn-fe
 

string-list.c

@@ -204,3 +204,56 @@ void unsorted_string_list_delete_item(struct string_list *list, int i, int free_
 	list->items[i] = list->items[list->nr-1];
 	list->nr--;
 }
+
+int string_list_split(struct string_list *list, const char *string,
+		      int delim, int maxsplit)
+{
+	int count = 0;
+	const char *p = string, *end;
+
+	if (!list->strdup_strings)
+		die("internal error in string_list_split(): "
+		    "list->strdup_strings must be set");
+	for (;;) {
+		count++;
+		if (maxsplit >= 0 && count > maxsplit) {
+			string_list_append(list, p);
+			return count;
+		}
+		end = strchr(p, delim);
+		if (end) {
+			string_list_append_nodup(list, xmemdupz(p, end - p));
+			p = end + 1;
+		} else {
+			string_list_append(list, p);
+			return count;
+		}
+	}
+}
+
+int string_list_split_in_place(struct string_list *list, char *string,
+			       int delim, int maxsplit)
+{
+	int count = 0;
+	char *p = string, *end;
+
+	if (list->strdup_strings)
+		die("internal error in string_list_split_in_place(): "
+		    "list->strdup_strings must not be set");
+	for (;;) {
+		count++;
+		if (maxsplit >= 0 && count > maxsplit) {
+			string_list_append(list, p);
+			return count;
+		}
+		end = strchr(p, delim);
+		if (end) {
+			*end = '\0';
+			string_list_append(list, p);
+			p = end + 1;
+		} else {
+			string_list_append(list, p);
+			return count;
+		}
+	}
+}

string-list.h

@@ -63,4 +63,33 @@ struct string_list_item *unsorted_string_list_lookup(struct string_list *list,
 						     const char *string);
 
 void unsorted_string_list_delete_item(struct string_list *list, int i, int free_util);
+
+/*
+ * Split string into substrings on character delim and append the
+ * substrings to list.  The input string is not modified.
+ * list->strdup_strings must be set, as new memory needs to be
+ * allocated to hold the substrings.  If maxsplit is non-negative,
+ * then split at most maxsplit times.  Return the number of substrings
+ * appended to list.
+ *
+ * Examples:
+ *   string_list_split(l, "foo:bar:baz", ':', -1) -> ["foo", "bar", "baz"]
+ *   string_list_split(l, "foo:bar:baz", ':', 0) -> ["foo:bar:baz"]
+ *   string_list_split(l, "foo:bar:baz", ':', 1) -> ["foo", "bar:baz"]
+ *   string_list_split(l, "foo:bar:", ':', -1) -> ["foo", "bar", ""]
+ *   string_list_split(l, "", ':', -1) -> [""]
+ *   string_list_split(l, ":", ':', -1) -> ["", ""]
+ */
+int string_list_split(struct string_list *list, const char *string,
+		      int delim, int maxsplit);
+
+/*
+ * Like string_list_split(), except that string is split in-place: the
+ * delimiter characters in string are overwritten with NULs, and the
+ * new string_list_items point into string (which therefore must not
+ * be modified or freed while the string_list is in use).
+ * list->strdup_strings must *not* be set.
+ */
+int string_list_split_in_place(struct string_list *list, char *string,
+			       int delim, int maxsplit);
 #endif /* STRING_LIST_H */

t/t0063-string-list.sh

@@ -0,0 +1,63 @@
+#!/bin/sh
+#
+# Copyright (c) 2012 Michael Haggerty
+#
+
+test_description='Test string list functionality'
+
+. ./test-lib.sh
+
+test_split () {
+	cat >expected &&
+	test_expect_success "split $1 at $2, max $3" "
+		test-string-list split '$1' '$2' '$3' >actual &&
+		test_cmp expected actual &&
+		test-string-list split_in_place '$1' '$2' '$3' >actual &&
+		test_cmp expected actual
+	"
+}
+
+test_split "foo:bar:baz" ":" "-1" <<EOF
+3
+[0]: "foo"
+[1]: "bar"
+[2]: "baz"
+EOF
+
+test_split "foo:bar:baz" ":" "0" <<EOF
+1
+[0]: "foo:bar:baz"
+EOF
+
+test_split "foo:bar:baz" ":" "1" <<EOF
+2
+[0]: "foo"
+[1]: "bar:baz"
+EOF
+
+test_split "foo:bar:baz" ":" "2" <<EOF
+3
+[0]: "foo"
+[1]: "bar"
+[2]: "baz"
+EOF
+
+test_split "foo:bar:" ":" "-1" <<EOF
+3
+[0]: "foo"
+[1]: "bar"
+[2]: ""
+EOF
+
+test_split "" ":" "-1" <<EOF
+1
+[0]: ""
+EOF
+
+test_split ":" ":" "-1" <<EOF
+2
+[0]: ""
+[1]: ""
+EOF
+
+test_done

test-string-list.c

@@ -0,0 +1,45 @@
+#include "cache.h"
+#include "string-list.h"
+
+void write_list(const struct string_list *list)
+{
+	int i;
+	for (i = 0; i < list->nr; i++)
+		printf("[%d]: \"%s\"\n", i, list->items[i].string);
+}
+
+int main(int argc, char **argv)
+{
+	if (argc == 5 && !strcmp(argv[1], "split")) {
+		struct string_list list = STRING_LIST_INIT_DUP;
+		int i;
+		const char *s = argv[2];
+		int delim = *argv[3];
+		int maxsplit = atoi(argv[4]);
+
+		i = string_list_split(&list, s, delim, maxsplit);
+		printf("%d\n", i);
+		write_list(&list);
+		string_list_clear(&list, 0);
+		return 0;
+	}
+
+	if (argc == 5 && !strcmp(argv[1], "split_in_place")) {
+		struct string_list list = STRING_LIST_INIT_NODUP;
+		int i;
+		char *s = xstrdup(argv[2]);
+		int delim = *argv[3];
+		int maxsplit = atoi(argv[4]);
+
+		i = string_list_split_in_place(&list, s, delim, maxsplit);
+		printf("%d\n", i);
+		write_list(&list);
+		string_list_clear(&list, 0);
+		free(s);
+		return 0;
+	}
+
+	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
+		argv[1] ? argv[1] : "(there was none)");
+	return 1;
+}