Merge branch 'mc/credential-helper-www-authenticate'

Allow information carried on the WWW-AUthenticate header to be
passed to the credential helpers.

* mc/credential-helper-www-authenticate:
  credential: add WWW-Authenticate header to cred requests
  http: read HTTP WWW-Authenticate response headers
  t5563: add tests for basic and anoymous HTTP access

Author: gitster

Documentation/git-credential.txt

@@ -113,7 +113,13 @@ separated by an `=` (equals) sign, followed by a newline.
 The key may contain any bytes except `=`, newline, or NUL. The value may
 contain any bytes except newline or NUL.
 
-In both cases, all bytes are treated as-is (i.e., there is no quoting,
+Attributes with keys that end with C-style array brackets `[]` can have
+multiple values. Each instance of a multi-valued attribute forms an
+ordered list of values - the order of the repeated attributes defines
+the order of the values. An empty multi-valued attribute (`key[]=\n`)
+acts to clear any previous entries and reset the list.
+
+In all cases, all bytes are treated as-is (i.e., there is no quoting,
 and one cannot transmit a value with newline or NUL in it). The list of
 attributes is terminated by a blank line or end-of-file.
 
@@ -166,6 +172,17 @@ empty string.
 Components which are missing from the URL (e.g., there is no
 username in the example above) will be left unset.
 
+`wwwauth[]`::
+
+	When an HTTP response is received by Git that includes one or more
+	'WWW-Authenticate' authentication headers, these will be passed by Git
+	to credential helpers.
++
+Each 'WWW-Authenticate' header value is passed as a multi-valued
+attribute 'wwwauth[]', where the order of the attributes is the same as
+they appear in the HTTP response. This attribute is 'one-way' from Git
+to pass additional information to credential helpers.
+
 Unrecognised attributes are silently discarded.
 
 GIT

credential.c

@@ -23,6 +23,7 @@ void credential_clear(struct credential *c)
 	free(c->username);
 	free(c->password);
 	string_list_clear(&c->helpers, 0);
+	strvec_clear(&c->wwwauth_headers);
 
 	credential_init(c);
 }
@@ -280,6 +281,8 @@ void credential_write(const struct credential *c, FILE *fp)
 		credential_write_item(fp, "password_expiry_utc", s, 0);
 		free(s);
 	}
+	for (size_t i = 0; i < c->wwwauth_headers.nr; i++)
+		credential_write_item(fp, "wwwauth[]", c->wwwauth_headers.v[i], 0);
 }
 
 static int run_credential_helper(struct credential *c,

credential.h

@@ -2,6 +2,7 @@
 #define CREDENTIAL_H
 
 #include "string-list.h"
+#include "strvec.h"
 
 /**
  * The credentials API provides an abstracted way of gathering username and
@@ -115,6 +116,20 @@ struct credential {
 	 */
 	struct string_list helpers;
 
+	/**
+	 * A `strvec` of WWW-Authenticate header values. Each string
+	 * is the value of a WWW-Authenticate header in an HTTP response,
+	 * in the order they were received in the response.
+	 */
+	struct strvec wwwauth_headers;
+
+	/**
+	 * Internal use only. Keeps track of if we previously matched against a
+	 * WWW-Authenticate header line in order to re-fold future continuation
+	 * lines into one value.
+	 */
+	unsigned header_is_last_match:1;
+
 	unsigned approved:1,
 		 configured:1,
 		 quit:1,
@@ -132,6 +147,7 @@ struct credential {
 #define CREDENTIAL_INIT { \
 	.helpers = STRING_LIST_INIT_DUP, \
 	.password_expiry_utc = TIME_MAX, \
+	.wwwauth_headers = STRVEC_INIT, \
 }
 
 /* Initialize a credential structure, setting all fields to empty. */

git-compat-util.h

@@ -1288,6 +1288,25 @@ static inline int skip_iprefix(const char *str, const char *prefix,
 	return 0;
 }
 
+/*
+ * Like skip_prefix_mem, but compare case-insensitively. Note that the
+ * comparison is done via tolower(), so it is strictly ASCII (no multi-byte
+ * characters or locale-specific conversions).
+ */
+static inline int skip_iprefix_mem(const char *buf, size_t len,
+				   const char *prefix,
+				   const char **out, size_t *outlen)
+{
+	do {
+		if (!*prefix) {
+			*out = buf;
+			*outlen = len;
+			return 1;
+		}
+	} while (len-- > 0 && tolower(*buf++) == tolower(*prefix++));
+	return 0;
+}
+
 static inline int strtoul_ui(char const *s, int base, unsigned int *result)
 {
 	unsigned long ul;

http.c

@@ -182,6 +182,115 @@ size_t fwrite_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_)
 	return nmemb;
 }
 
+/*
+ * A folded header continuation line starts with any number of spaces or
+ * horizontal tab characters (SP or HTAB) as per RFC 7230 section 3.2.
+ * It is not a continuation line if the line starts with any other character.
+ */
+static inline int is_hdr_continuation(const char *ptr, const size_t size)
+{
+	return size && (*ptr == ' ' || *ptr == '\t');
+}
+
+static size_t fwrite_wwwauth(char *ptr, size_t eltsize, size_t nmemb, void *p)
+{
+	size_t size = eltsize * nmemb;
+	struct strvec *values = &http_auth.wwwauth_headers;
+	struct strbuf buf = STRBUF_INIT;
+	const char *val;
+	size_t val_len;
+
+	/*
+	 * Header lines may not come NULL-terminated from libcurl so we must
+	 * limit all scans to the maximum length of the header line, or leverage
+	 * strbufs for all operations.
+	 *
+	 * In addition, it is possible that header values can be split over
+	 * multiple lines as per RFC 7230. 'Line folding' has been deprecated
+	 * but older servers may still emit them. A continuation header field
+	 * value is identified as starting with a space or horizontal tab.
+	 *
+	 * The formal definition of a header field as given in RFC 7230 is:
+	 *
+	 * header-field   = field-name ":" OWS field-value OWS
+	 *
+	 * field-name     = token
+	 * field-value    = *( field-content / obs-fold )
+	 * field-content  = field-vchar [ 1*( SP / HTAB ) field-vchar ]
+	 * field-vchar    = VCHAR / obs-text
+	 *
+	 * obs-fold       = CRLF 1*( SP / HTAB )
+	 *                ; obsolete line folding
+	 *                ; see Section 3.2.4
+	 */
+
+	/* Start of a new WWW-Authenticate header */
+	if (skip_iprefix_mem(ptr, size, "www-authenticate:", &val, &val_len)) {
+		strbuf_add(&buf, val, val_len);
+
+		/*
+		 * Strip the CRLF that should be present at the end of each
+		 * field as well as any trailing or leading whitespace from the
+		 * value.
+		 */
+		strbuf_trim(&buf);
+
+		strvec_push(values, buf.buf);
+		http_auth.header_is_last_match = 1;
+		goto exit;
+	}
+
+	/*
+	 * This line could be a continuation of the previously matched header
+	 * field. If this is the case then we should append this value to the
+	 * end of the previously consumed value.
+	 */
+	if (http_auth.header_is_last_match && is_hdr_continuation(ptr, size)) {
+		/*
+		 * Trim the CRLF and any leading or trailing from this line.
+		 */
+		strbuf_add(&buf, ptr, size);
+		strbuf_trim(&buf);
+
+		/*
+		 * At this point we should always have at least one existing
+		 * value, even if it is empty. Do not bother appending the new
+		 * value if this continuation header is itself empty.
+		 */
+		if (!values->nr) {
+			BUG("should have at least one existing header value");
+		} else if (buf.len) {
+			char *prev = xstrdup(values->v[values->nr - 1]);
+
+			/* Join two non-empty values with a single space. */
+			const char *const sp = *prev ? " " : "";
+
+			strvec_pop(values);
+			strvec_pushf(values, "%s%s%s", prev, sp, buf.buf);
+			free(prev);
+		}
+
+		goto exit;
+	}
+
+	/* Not a continuation of a previously matched auth header line. */
+	http_auth.header_is_last_match = 0;
+
+	/*
+	 * If this is a HTTP status line and not a header field, this signals
+	 * a different HTTP response. libcurl writes all the output of all
+	 * response headers of all responses, including redirects.
+	 * We only care about the last HTTP request response's headers so clear
+	 * the existing array.
+	 */
+	if (skip_iprefix_mem(ptr, size, "http/", &val, &val_len))
+		strvec_clear(values);
+
+exit:
+	strbuf_release(&buf);
+	return size;
+}
+
 size_t fwrite_null(char *ptr, size_t eltsize, size_t nmemb, void *strbuf)
 {
 	return nmemb;
@@ -1896,6 +2005,8 @@ static int http_request(const char *url,
 					 fwrite_buffer);
 	}
 
+	curl_easy_setopt(slot->curl, CURLOPT_HEADERFUNCTION, fwrite_wwwauth);
+
 	accept_language = http_get_accept_language_header();
 
 	if (accept_language)

t/lib-httpd.sh

@@ -142,6 +142,7 @@ prepare_httpd() {
 	install_script error-smart-http.sh
 	install_script error.sh
 	install_script apply-one-time-perl.sh
+	install_script nph-custom-auth.sh
 
 	ln -s "$LIB_HTTPD_MODULE_PATH" "$HTTPD_ROOT_PATH/modules"
 

t/lib-httpd/apache.conf

@@ -141,6 +141,11 @@ Alias /auth/dumb/ www/auth/dumb/
 	SetEnv GIT_HTTP_EXPORT_ALL
 	SetEnv GIT_PROTOCOL
 </LocationMatch>
+<LocationMatch /custom_auth/>
+	SetEnv GIT_EXEC_PATH ${GIT_EXEC_PATH}
+	SetEnv GIT_HTTP_EXPORT_ALL
+	CGIPassAuth on
+</LocationMatch>
 ScriptAlias /smart/incomplete_length/git-upload-pack incomplete-length-upload-pack-v2-http.sh/
 ScriptAlias /smart/incomplete_body/git-upload-pack incomplete-body-upload-pack-v2-http.sh/
 ScriptAlias /smart/no_report/git-receive-pack error-no-report.sh/
@@ -150,6 +155,7 @@ ScriptAlias /broken_smart/ broken-smart-http.sh/
 ScriptAlias /error_smart/ error-smart-http.sh/
 ScriptAlias /error/ error.sh/
 ScriptAliasMatch /one_time_perl/(.*) apply-one-time-perl.sh/$1
+ScriptAliasMatch /custom_auth/(.*) nph-custom-auth.sh/$1
 <Directory ${GIT_EXEC_PATH}>
 	Options FollowSymlinks
 </Directory>

t/lib-httpd/nph-custom-auth.sh

@@ -0,0 +1,39 @@
+#!/bin/sh
+
+VALID_CREDS_FILE=custom-auth.valid
+CHALLENGE_FILE=custom-auth.challenge
+
+#
+# If $VALID_CREDS_FILE exists in $HTTPD_ROOT_PATH, consider each line as a valid
+# credential for the current request. Each line in the file is considered a
+# valid HTTP Authorization header value. For example:
+#
+# Basic YWxpY2U6c2VjcmV0LXBhc3N3ZA==
+#
+# If $CHALLENGE_FILE exists in $HTTPD_ROOT_PATH, output the contents as headers
+# in a 401 response if no valid authentication credentials were included in the
+# request. For example:
+#
+# WWW-Authenticate: Bearer authorize_uri="id.example.com" p=1 q=0
+# WWW-Authenticate: Basic realm="example.com"
+#
+
+if test -n "$HTTP_AUTHORIZATION" && \
+	grep -Fqsx "${HTTP_AUTHORIZATION}" "$VALID_CREDS_FILE"
+then
+	# Note that although git-http-backend returns a status line, it
+	# does so using a CGI 'Status' header. Because this script is an
+	# No Parsed Headers (NPH) script, we must return a real HTTP
+	# status line.
+	# This is only a test script, so we don't bother to check for
+	# the actual status from git-http-backend and always return 200.
+	echo 'HTTP/1.1 200 OK'
+	exec "$GIT_EXEC_PATH"/git-http-backend
+fi
+
+echo 'HTTP/1.1 401 Authorization Required'
+if test -f "$CHALLENGE_FILE"
+then
+	cat "$CHALLENGE_FILE"
+fi
+echo