Merge branch 'jc/url-match'

Allow section.<urlpattern>.var configuration variables to be
treated as a "virtual" section.var given a URL, and use the
mechanism to enhance http.* configuration variables.

This is a reroll of Kyle J. McKay's work.

* jc/url-match:
  builtin/config.c: compilation fix
  config: "git config --get-urlmatch" parses section.<url>.key
  builtin/config: refactor collect_config()
  config: parse http.<url>.<variable> using urlmatch
  config: add generic callback wrapper to parse section.<url>.key
  config: add helper to normalize and match URLs
  http.c: fix parsing of http.sslCertPasswordProtected variable

Author: gitster

.gitignore

@@ -202,6 +202,7 @@
 /test-string-list
 /test-subprocess
 /test-svn-fe
+/test-urlmatch-normalization
 /test-wildmatch
 /common-cmds.h
 *.tar.gz

Documentation/config.txt

@@ -1533,6 +1533,51 @@ http.useragent::
 	of common USER_AGENT strings (but not including those like git/1.7.1).
 	Can be overridden by the 'GIT_HTTP_USER_AGENT' environment variable.
 
+http.<url>.*::
+	Any of the http.* options above can be applied selectively to some urls.
+	For a config key to match a URL, each element of the config key is
+	compared to that of the URL, in the following order:
++
+--
+. Scheme (e.g., `https` in `https://example.com/`). This field
+  must match exactly between the config key and the URL.
+
+. Host/domain name (e.g., `example.com` in `https://example.com/`).
+  This field must match exactly between the config key and the URL.
+
+. Port number (e.g., `8080` in `http://example.com:8080/`).
+  This field must match exactly between the config key and the URL.
+  Omitted port numbers are automatically converted to the correct
+  default for the scheme before matching.
+
+. Path (e.g., `repo.git` in `https://example.com/repo.git`). The
+  path field of the config key must match the path field of the URL
+  either exactly or as a prefix of slash-delimited path elements.  This means
+  a config key with path `foo/` matches URL path `foo/bar`.  A prefix can only
+  match on a slash (`/`) boundary.  Longer matches take precedence (so a config
+  key with path `foo/bar` is a better match to URL path `foo/bar` than a config
+  key with just path `foo/`).
+
+. User name (e.g., `user` in `https://[email protected]/repo.git`). If
+  the config key has a user name it must match the user name in the
+  URL exactly. If the config key does not have a user name, that
+  config key will match a URL with any user name (including none),
+  but at a lower precedence than a config key with a user name.
+--
++
+The list above is ordered by decreasing precedence; a URL that matches
+a config key's path is preferred to one that matches its user name. For example,
+if the URL is `https://[email protected]/foo/bar` a config key match of
+`https://example.com/foo` will be preferred over a config key match of
+`https://[email protected]`.
++
+All URLs are normalized before attempting any matching (the password part,
+if embedded in the URL, is always ignored for matching purposes) so that
+equivalent urls that are simply spelled differently will match properly.
+Environment variable settings always override any matches.  The urls that are
+matched against are those given directly to Git commands.  This means any URLs
+visited as a result of a redirection do not participate in matching.
+
 i18n.commitEncoding::
 	Character encoding the commit messages are stored in; Git itself
 	does not care per se, but this information is necessary e.g. when

Documentation/git-config.txt

@@ -15,6 +15,7 @@ SYNOPSIS
 'git config' [<file-option>] [type] [-z|--null] --get name [value_regex]
 'git config' [<file-option>] [type] [-z|--null] --get-all name [value_regex]
 'git config' [<file-option>] [type] [-z|--null] --get-regexp name_regex [value_regex]
+'git config' [<file-option>] [type] [-z|--null] --get-urlmatch name URL
 'git config' [<file-option>] --unset name [value_regex]
 'git config' [<file-option>] --unset-all name [value_regex]
 'git config' [<file-option>] --rename-section old_name new_name
@@ -95,6 +96,14 @@ OPTIONS
 	in which section and variable names are lowercased, but subsection
 	names are not.
 
+--get-urlmatch name URL::
+	When given a two-part name section.key, the value for
+	section.<url>.key whose <url> part matches the best to the
+	given URL is returned (if no such key exists, the value for
+	section.key is used as a fallback).  When given just the
+	section as name, do so for all the keys in the section and
+	list them.
+
 --global::
 	For writing options: write to global `~/.gitconfig` file
 	rather than the repository `.git/config`, write to
@@ -295,6 +304,13 @@ Given a .git/config like this:
 		gitproxy=proxy-command for kernel.org
 		gitproxy=default-proxy ; for all the rest
 
+	; HTTP
+	[http]
+		sslVerify
+	[http "https://weak.example.com"]
+		sslVerify = false
+		cookieFile = /tmp/cookie.txt
+
 you can set the filemode to true with
 
 ------------
@@ -380,6 +396,19 @@ RESET=$(git config --get-color "" "reset")
 echo "${WS}your whitespace color or blue reverse${RESET}"
 ------------
 
+For URLs in `https://weak.example.com`, `http.sslVerify` is set to
+false, while it is set to `true` for all others:
+
+------------
+% git config --bool --get-urlmatch http.sslverify https://good.example.com
+true
+% git config --bool --get-urlmatch http.sslverify https://weak.example.com
+false
+% git config --get-urlmatch http https://weak.example.com
+http.cookiefile /tmp/cookie.txt
+http.sslverify false
+------------
+
 include::config.txt[]
 
 GIT

Makefile

@@ -580,6 +580,7 @@ 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
+TEST_PROGRAMS_NEED_X += test-urlmatch-normalization
 TEST_PROGRAMS_NEED_X += test-wildmatch
 
 TEST_PROGRAMS = $(patsubst %,%$X,$(TEST_PROGRAMS_NEED_X))
@@ -736,6 +737,7 @@ LIB_H += tree-walk.h
 LIB_H += tree.h
 LIB_H += unpack-trees.h
 LIB_H += url.h
+LIB_H += urlmatch.h
 LIB_H += userdiff.h
 LIB_H += utf8.h
 LIB_H += varint.h
@@ -886,6 +888,7 @@ LIB_OBJS += tree.o
 LIB_OBJS += tree-walk.o
 LIB_OBJS += unpack-trees.o
 LIB_OBJS += url.o
+LIB_OBJS += urlmatch.o
 LIB_OBJS += usage.o
 LIB_OBJS += userdiff.o
 LIB_OBJS += utf8.o

builtin/config.c

@@ -2,6 +2,7 @@
 #include "cache.h"
 #include "color.h"
 #include "parse-options.h"
+#include "urlmatch.h"
 
 static const char *const builtin_config_usage[] = {
 	N_("git config [options]"),
@@ -42,6 +43,7 @@ static int respect_includes = -1;
 #define ACTION_SET_ALL (1<<12)
 #define ACTION_GET_COLOR (1<<13)
 #define ACTION_GET_COLORBOOL (1<<14)
+#define ACTION_GET_URLMATCH (1<<15)
 
 #define TYPE_BOOL (1<<0)
 #define TYPE_INT (1<<1)
@@ -59,6 +61,7 @@ static struct option builtin_config_options[] = {
 	OPT_BIT(0, "get", &actions, N_("get value: name [value-regex]"), ACTION_GET),
 	OPT_BIT(0, "get-all", &actions, N_("get all values: key [value-regex]"), ACTION_GET_ALL),
 	OPT_BIT(0, "get-regexp", &actions, N_("get values for regexp: name-regex [value-regex]"), ACTION_GET_REGEXP),
+	OPT_BIT(0, "get-urlmatch", &actions, N_("get value specific for the URL: section[.var] URL"), ACTION_GET_URLMATCH),
 	OPT_BIT(0, "replace-all", &actions, N_("replace all matching variables: name value [value_regex]"), ACTION_REPLACE_ALL),
 	OPT_BIT(0, "add", &actions, N_("add a new variable: name value"), ACTION_ADD),
 	OPT_BIT(0, "unset", &actions, N_("remove a variable: name [value-regex]"), ACTION_UNSET),
@@ -102,33 +105,21 @@ struct strbuf_list {
 	int alloc;
 };
 
-static int collect_config(const char *key_, const char *value_, void *cb)
+static int format_config(struct strbuf *buf, const char *key_, const char *value_)
 {
-	struct strbuf_list *values = cb;
-	struct strbuf *buf;
-	char value[256];
-	const char *vptr = value;
 	int must_free_vptr = 0;
 	int must_print_delim = 0;
+	char value[256];
+	const char *vptr = value;
 
-	if (!use_key_regexp && strcmp(key_, key))
-		return 0;
-	if (use_key_regexp && regexec(key_regexp, key_, 0, NULL, 0))
-		return 0;
-	if (regexp != NULL &&
-	    (do_not_match ^ !!regexec(regexp, (value_?value_:""), 0, NULL, 0)))
-		return 0;
-
-	ALLOC_GROW(values->items, values->nr + 1, values->alloc);
-	buf = &values->items[values->nr++];
 	strbuf_init(buf, 0);
 
 	if (show_keys) {
 		strbuf_addstr(buf, key_);
 		must_print_delim = 1;
 	}
 	if (types == TYPE_INT)
-		sprintf(value, "%d", git_config_int(key_, value_?value_:""));
+		sprintf(value, "%d", git_config_int(key_, value_ ? value_ : ""));
 	else if (types == TYPE_BOOL)
 		vptr = git_config_bool(key_, value_) ? "true" : "false";
 	else if (types == TYPE_BOOL_OR_INT) {
@@ -156,15 +147,27 @@ static int collect_config(const char *key_, const char *value_, void *cb)
 	strbuf_addch(buf, term);
 
 	if (must_free_vptr)
-		/* If vptr must be freed, it's a pointer to a
-		 * dynamically allocated buffer, it's safe to cast to
-		 * const.
-		*/
 		free((char *)vptr);
-
 	return 0;
 }
 
+static int collect_config(const char *key_, const char *value_, void *cb)
+{
+	struct strbuf_list *values = cb;
+
+	if (!use_key_regexp && strcmp(key_, key))
+		return 0;
+	if (use_key_regexp && regexec(key_regexp, key_, 0, NULL, 0))
+		return 0;
+	if (regexp != NULL &&
+	    (do_not_match ^ !!regexec(regexp, (value_?value_:""), 0, NULL, 0)))
+		return 0;
+
+	ALLOC_GROW(values->items, values->nr + 1, values->alloc);
+
+	return format_config(&values->items[values->nr++], key_, value_);
+}
+
 static int get_value(const char *key_, const char *regex_)
 {
 	int ret = CONFIG_GENERIC_ERROR;
@@ -364,6 +367,97 @@ static void check_blob_write(void)
 		die("writing config blobs is not supported");
 }
 
+struct urlmatch_current_candidate_value {
+	char value_is_null;
+	struct strbuf value;
+};
+
+static int urlmatch_collect_fn(const char *var, const char *value, void *cb)
+{
+	struct string_list *values = cb;
+	struct string_list_item *item = string_list_insert(values, var);
+	struct urlmatch_current_candidate_value *matched = item->util;
+
+	if (!matched) {
+		matched = xmalloc(sizeof(*matched));
+		strbuf_init(&matched->value, 0);
+		item->util = matched;
+	} else {
+		strbuf_reset(&matched->value);
+	}
+
+	if (value) {
+		strbuf_addstr(&matched->value, value);
+		matched->value_is_null = 0;
+	} else {
+		matched->value_is_null = 1;
+	}
+	return 0;
+}
+
+static char *dup_downcase(const char *string)
+{
+	char *result;
+	size_t len, i;
+
+	len = strlen(string);
+	result = xmalloc(len + 1);
+	for (i = 0; i < len; i++)
+		result[i] = tolower(string[i]);
+	result[i] = '\0';
+	return result;
+}
+
+static int get_urlmatch(const char *var, const char *url)
+{
+	char *section_tail;
+	struct string_list_item *item;
+	struct urlmatch_config config = { STRING_LIST_INIT_DUP };
+	struct string_list values = STRING_LIST_INIT_DUP;
+
+	config.collect_fn = urlmatch_collect_fn;
+	config.cascade_fn = NULL;
+	config.cb = &values;
+
+	if (!url_normalize(url, &config.url))
+		die("%s", config.url.err);
+
+	config.section = dup_downcase(var);
+	section_tail = strchr(config.section, '.');
+	if (section_tail) {
+		*section_tail = '\0';
+		config.key = section_tail + 1;
+		show_keys = 0;
+	} else {
+		config.key = NULL;
+		show_keys = 1;
+	}
+
+	git_config_with_options(urlmatch_config_entry, &config,
+				given_config_file, NULL, respect_includes);
+
+	for_each_string_list_item(item, &values) {
+		struct urlmatch_current_candidate_value *matched = item->util;
+		struct strbuf key = STRBUF_INIT;
+		struct strbuf buf = STRBUF_INIT;
+
+		strbuf_addstr(&key, item->string);
+		format_config(&buf, key.buf,
+			      matched->value_is_null ? NULL : matched->value.buf);
+		fwrite(buf.buf, 1, buf.len, stdout);
+		strbuf_release(&key);
+		strbuf_release(&buf);
+
+		strbuf_release(&matched->value);
+	}
+	string_list_clear(&config.vars, 1);
+	string_list_clear(&values, 1);
+	free(config.url.url);
+
+	free((void *)config.section);
+	return 0;
+}
+
 int cmd_config(int argc, const char **argv, const char *prefix)
 {
 	int nongit = !startup_info->have_repository;
@@ -523,6 +617,10 @@ int cmd_config(int argc, const char **argv, const char *prefix)
 		check_argc(argc, 1, 2);
 		return get_value(argv[0], argv[1]);
 	}
+	else if (actions == ACTION_GET_URLMATCH) {
+		check_argc(argc, 2, 2);
+		return get_urlmatch(argv[0], argv[1]);
+	}
 	else if (actions == ACTION_UNSET) {
 		check_blob_write();
 		check_argc(argc, 1, 2);

http.c

@@ -3,6 +3,7 @@
 #include "sideband.h"
 #include "run-command.h"
 #include "url.h"
+#include "urlmatch.h"
 #include "credential.h"
 #include "version.h"
 #include "pkt-line.h"
@@ -161,8 +162,7 @@ static int http_options(const char *var, const char *value, void *cb)
 	if (!strcmp("http.sslcainfo", var))
 		return git_config_string(&ssl_cainfo, var, value);
 	if (!strcmp("http.sslcertpasswordprotected", var)) {
-		if (git_config_bool(var, value))
-			ssl_cert_password_required = 1;
+		ssl_cert_password_required = git_config_bool(var, value);
 		return 0;
 	}
 	if (!strcmp("http.ssltry", var)) {
@@ -346,10 +346,20 @@ void http_init(struct remote *remote, const char *url, int proactive_auth)
 {
 	char *low_speed_limit;
 	char *low_speed_time;
+	char *normalized_url;
+	struct urlmatch_config config = { STRING_LIST_INIT_DUP };
+
+	config.section = "http";
+	config.key = NULL;
+	config.collect_fn = http_options;
+	config.cascade_fn = git_default_config;
+	config.cb = NULL;
 
 	http_is_verbose = 0;
+	normalized_url = url_normalize(url, &config.url);
 
-	git_config(http_options, NULL);
+	git_config(urlmatch_config_entry, &config);
+	free(normalized_url);
 
 	curl_global_init(CURL_GLOBAL_ALL);
 

t/.gitattributes

@@ -1 +1,2 @@
 t[0-9][0-9][0-9][0-9]/* -whitespace
+t0110/url-* binary