Restrict repository indexing by glob match (#7767)

* Restrict repository indexing by file extension

* Use REPO_EXTENSIONS_LIST_INCLUDE instead of REPO_EXTENSIONS_LIST_EXCLUDE and have a more flexible extension pattern

* Corrected to pass lint gosimple

* Add wildcard support to REPO_INDEXER_EXTENSIONS

* This reverts commit 72a650c8e4.

* Add wildcard support to REPO_INDEXER_EXTENSIONS (no make vendor)

* Simplify isIndexable() for better clarity

* Add gobwas/glob to vendors

* manually set appengine new release

* Implement better REPO_INDEXER_INCLUDE and REPO_INDEXER_EXCLUDE

* Add unit and integration tests

* Update app.ini.sample and reword config-cheat-sheet

* Add doc page and correct app.ini.sample

* Some polish on the doc

* Simplify code as suggested by @lafriks

custom/conf/app.ini.sample

@@ -302,6 +302,11 @@ REPO_INDEXER_ENABLED = false
 REPO_INDEXER_PATH = indexers/repos.bleve
 UPDATE_BUFFER_LEN = 20
 MAX_FILE_SIZE = 1048576
+; A comma separated list of glob patterns (see https://github.com/gobwas/glob) to include
+; in the index; default is empty
+REPO_INDEXER_INCLUDE =
+; A comma separated list of glob patterns to exclude from the index; ; default is empty
+REPO_INDEXER_EXCLUDE =
 
 [admin]
 ; Disallow regular (non-admin) users from creating organizations.

docs/content/doc/advanced/config-cheat-sheet.en-us.md

@@ -181,6 +181,8 @@ Values containing `#` or `;` must be quoted using `` ` `` or `"""`.
 
 - `REPO_INDEXER_ENABLED`: **false**: Enables code search (uses a lot of disk space, about 6 times more than the repository size).
 - `REPO_INDEXER_PATH`: **indexers/repos.bleve**: Index file used for code search.
+- `REPO_INDEXER_INCLUDE`: **empty**: A comma separated list of glob patterns (see https://github.com/gobwas/glob) to **include** in the index. Use `**.txt` to match any files with .txt extension. An empty list means include all files.
+- `REPO_INDEXER_EXCLUDE`: **empty**: A comma separated list of glob patterns (see https://github.com/gobwas/glob) to **exclude** from the index. Files that match this list will not be indexed, even if they match in `REPO_INDEXER_INCLUDE`.
 - `UPDATE_BUFFER_LEN`: **20**: Buffer length of index request.
 - `MAX_FILE_SIZE`: **1048576**: Maximum size in bytes of files to be indexed.
 

docs/content/doc/advanced/repo-indexer.en-us.md

@@ -0,0 +1,58 @@
+---
+date: "2019-09-06T01:35:00-03:00"
+title: "Repository indexer"
+slug: "repo-indexer"
+weight: 45
+toc: true
+draft: false
+menu:
+  sidebar:
+    parent: "advanced"
+    name: "Repository indexer"
+    weight: 45
+    identifier: "repo-indexer"
+---
+
+# Repository indexer
+
+## Setting up the repository indexer
+
+Gitea can search through the files of the repositories by enabling this function in your [`app.ini`](https://docs.gitea.io/en-us/config-cheat-sheet/):
+
+```
+[indexer]
+; ...
+REPO_INDEXER_ENABLED = true
+REPO_INDEXER_PATH = indexers/repos.bleve
+UPDATE_BUFFER_LEN = 20
+MAX_FILE_SIZE = 1048576
+REPO_INDEXER_INCLUDE =
+REPO_INDEXER_EXCLUDE = resources/bin/**
+```
+
+Please bear in mind that indexing the contents can consume a lot of system resources, especially when the index is created for the first time or globally updated (e.g. after upgrading Gitea).
+
+### Choosing the files for indexing by size
+
+The `MAX_FILE_SIZE` option will make the indexer skip all files larger than the specified value.
+
+### Choosing the files for indexing by path
+
+Gitea applies glob pattern matching from the [`gobwas/glob` library](https://github.com/gobwas/glob) to choose which files will be included in the index.
+
+Limiting the list of files prevents the indexes from becoming polluted with derived or irrelevant files (e.g. lss, sym, map, etc.), so the search results are more relevant. It can also help reduce the index size.
+
+`REPO_INDEXER_INCLUDE` (default: empty) is a comma separated list of glob patterns to **include** in the index. An empty list means "_include all files_".
+`REPO_INDEXER_EXCLUDE` (default: empty) is a comma separated list of glob patterns to **exclude** from the index. Files that match this list will not be indexed. `REPO_INDEXER_EXCLUDE` takes precedence over `REPO_INDEXER_INCLUDE`.
+
+Pattern matching works as follows:
+
+* To match all files with a `.txt` extension no matter what directory, use `**.txt`.
+* To match all files with a `.txt` extension _only at the root level of the repository_, use `*.txt`.
+* To match all files inside `resources/bin` and below, use `resources/bin/**`.
+* To match all files _immediately inside_ `resources/bin`, use `resources/bin/*`.
+* To match all files named `Makefile`, use `**Makefile`.
+* Matching a directory has no effect; the pattern `resources/bin` will not include/exclude files inside that directory; `resources/bin/**` will.
+* All files and patterns are normalized to lower case, so `**Makefile`, `**makefile` and `**MAKEFILE` are equivalent.
+
+

integrations/api_repo_test.go

@@ -70,9 +70,9 @@ func TestAPISearchRepo(t *testing.T) {
 		expectedResults
 	}{
 		{name: "RepositoriesMax50", requestURL: "/api/v1/repos/search?limit=50&private=false", expectedResults: expectedResults{
-			nil:   {count: 21},
-			user:  {count: 21},
-			user2: {count: 21}},
+			nil:   {count: 22},
+			user:  {count: 22},
+			user2: {count: 22}},
 		},
 		{name: "RepositoriesMax10", requestURL: "/api/v1/repos/search?limit=10&private=false", expectedResults: expectedResults{
 			nil:   {count: 10},

integrations/gitea-repositories-meta/user2/glob.git/HEAD

@@ -0,0 +1 @@
+ref: refs/heads/master

integrations/gitea-repositories-meta/user2/glob.git/config

@@ -0,0 +1,4 @@
+[core]
+	repositoryformatversion = 0
+	filemode = true
+	bare = true

integrations/gitea-repositories-meta/user2/glob.git/description

@@ -0,0 +1 @@
+Unnamed repository; edit this file 'description' to name the repository.

integrations/gitea-repositories-meta/user2/glob.git/hooks/applypatch-msg.sample

@@ -0,0 +1,15 @@
+#!/bin/sh
+#
+# An example hook script to check the commit log message taken by
+# applypatch from an e-mail message.
+#
+# The hook should exit with non-zero status after issuing an
+# appropriate message if it wants to stop the commit.  The hook is
+# allowed to edit the commit message file.
+#
+# To enable this hook, rename this file to "applypatch-msg".
+
+. git-sh-setup
+commitmsg="$(git rev-parse --git-path hooks/commit-msg)"
+test -x "$commitmsg" && exec "$commitmsg" ${1+"$@"}
+:

integrations/gitea-repositories-meta/user2/glob.git/hooks/commit-msg.sample

@@ -0,0 +1,24 @@
+#!/bin/sh
+#
+# An example hook script to check the commit log message.
+# Called by "git commit" with one argument, the name of the file
+# that has the commit message.  The hook should exit with non-zero
+# status after issuing an appropriate message if it wants to stop the
+# commit.  The hook is allowed to edit the commit message file.
+#
+# To enable this hook, rename this file to "commit-msg".
+
+# Uncomment the below to add a Signed-off-by line to the message.
+# Doing this in a hook is a bad idea in general, but the prepare-commit-msg
+# hook is more suited to it.
+#
+# SOB=$(git var GIT_AUTHOR_IDENT | sed -n 's/^\(.*>\).*$/Signed-off-by: \1/p')
+# grep -qs "^$SOB" "$1" || echo "$SOB" >> "$1"
+
+# This example catches duplicate Signed-off-by lines.
+
+test "" = "$(grep '^Signed-off-by: ' "$1" |
+	 sort | uniq -c | sed -e '/^[ 	]*1[ 	]/d')" || {
+	echo >&2 Duplicate Signed-off-by lines.
+	exit 1
+}

integrations/gitea-repositories-meta/user2/glob.git/hooks/fsmonitor-watchman.sample

@@ -0,0 +1,114 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use IPC::Open2;
+
+# An example hook script to integrate Watchman
+# (https://facebook.github.io/watchman/) with git to speed up detecting
+# new and modified files.
+#
+# The hook is passed a version (currently 1) and a time in nanoseconds
+# formatted as a string and outputs to stdout all files that have been
+# modified since the given time. Paths must be relative to the root of
+# the working tree and separated by a single NUL.
+#
+# To enable this hook, rename this file to "query-watchman" and set
+# 'git config core.fsmonitor .git/hooks/query-watchman'
+#
+my ($version, $time) = @ARGV;
+
+# Check the hook interface version
+
+if ($version == 1) {
+	# convert nanoseconds to seconds
+	$time = int $time / 1000000000;
+} else {
+	die "Unsupported query-fsmonitor hook version '$version'.\n" .
+	    "Falling back to scanning...\n";
+}
+
+my $git_work_tree;
+if ($^O =~ 'msys' || $^O =~ 'cygwin') {
+	$git_work_tree = Win32::GetCwd();
+	$git_work_tree =~ tr/\\/\//;
+} else {
+	require Cwd;
+	$git_work_tree = Cwd::cwd();
+}
+
+my $retry = 1;
+
+launch_watchman();
+
+sub launch_watchman {
+
+	my $pid = open2(\*CHLD_OUT, \*CHLD_IN, 'watchman -j --no-pretty')
+	    or die "open2() failed: $!\n" .
+	    "Falling back to scanning...\n";
+
+	# In the query expression below we're asking for names of files that
+	# changed since $time but were not transient (ie created after
+	# $time but no longer exist).
+	#
+	# To accomplish this, we're using the "since" generator to use the
+	# recency index to select candidate nodes and "fields" to limit the
+	# output to file names only. Then we're using the "expression" term to
+	# further constrain the results.
+	#
+	# The category of transient files that we want to ignore will have a
+	# creation clock (cclock) newer than $time_t value and will also not
+	# currently exist.
+
+	my $query = <<"	END";
+		["query", "$git_work_tree", {
+			"since": $time,
+			"fields": ["name"],
+			"expression": ["not", ["allof", ["since", $time, "cclock"], ["not", "exists"]]]
+		}]
+	END
+
+	print CHLD_IN $query;
+	close CHLD_IN;
+	my $response = do {local $/; <CHLD_OUT>};
+
+	die "Watchman: command returned no output.\n" .
+	    "Falling back to scanning...\n" if $response eq "";
+	die "Watchman: command returned invalid output: $response\n" .
+	    "Falling back to scanning...\n" unless $response =~ /^\{/;
+
+	my $json_pkg;
+	eval {
+		require JSON::XS;
+		$json_pkg = "JSON::XS";
+		1;
+	} or do {
+		require JSON::PP;
+		$json_pkg = "JSON::PP";
+	};
+
+	my $o = $json_pkg->new->utf8->decode($response);
+
+	if ($retry > 0 and $o->{error} and $o->{error} =~ m/unable to resolve root .* directory (.*) is not watched/) {
+		print STDERR "Adding '$git_work_tree' to watchman's watch list.\n";
+		$retry--;
+		qx/watchman watch "$git_work_tree"/;
+		die "Failed to make watchman watch '$git_work_tree'.\n" .
+		    "Falling back to scanning...\n" if $? != 0;
+
+		# Watchman will always return all files on the first query so
+		# return the fast "everything is dirty" flag to git and do the
+		# Watchman query just to get it over with now so we won't pay
+		# the cost in git to look up each individual file.
+		print "/\0";
+		eval { launch_watchman() };
+		exit 0;
+	}
+
+	die "Watchman: $o->{error}.\n" .
+	    "Falling back to scanning...\n" if $o->{error};
+
+	binmode STDOUT, ":utf8";
+	local $, = "\0";
+	print @{$o->{files}};
+}

integrations/gitea-repositories-meta/user2/glob.git/hooks/post-update.sample

@@ -0,0 +1,8 @@
+#!/bin/sh
+#
+# An example hook script to prepare a packed repository for use over
+# dumb transports.
+#
+# To enable this hook, rename this file to "post-update".
+
+exec git update-server-info

integrations/gitea-repositories-meta/user2/glob.git/hooks/pre-applypatch.sample

@@ -0,0 +1,14 @@
+#!/bin/sh
+#
+# An example hook script to verify what is about to be committed
+# by applypatch from an e-mail message.
+#
+# The hook should exit with non-zero status after issuing an
+# appropriate message if it wants to stop the commit.
+#
+# To enable this hook, rename this file to "pre-applypatch".
+
+. git-sh-setup
+precommit="$(git rev-parse --git-path hooks/pre-commit)"
+test -x "$precommit" && exec "$precommit" ${1+"$@"}
+:

integrations/gitea-repositories-meta/user2/glob.git/hooks/pre-commit.sample

@@ -0,0 +1,49 @@
+#!/bin/sh
+#
+# An example hook script to verify what is about to be committed.
+# Called by "git commit" with no arguments.  The hook should
+# exit with non-zero status after issuing an appropriate message if
+# it wants to stop the commit.
+#
+# To enable this hook, rename this file to "pre-commit".
+
+if git rev-parse --verify HEAD >/dev/null 2>&1
+then
+	against=HEAD
+else
+	# Initial commit: diff against an empty tree object
+	against=$(git hash-object -t tree /dev/null)
+fi
+
+# If you want to allow non-ASCII filenames set this variable to true.
+allownonascii=$(git config --bool hooks.allownonascii)
+
+# Redirect output to stderr.
+exec 1>&2
+
+# Cross platform projects tend to avoid non-ASCII filenames; prevent
+# them from being added to the repository. We exploit the fact that the
+# printable range starts at the space character and ends with tilde.
+if [ "$allownonascii" != "true" ] &&
+	# Note that the use of brackets around a tr range is ok here, (it's
+	# even required, for portability to Solaris 10's /usr/bin/tr), since
+	# the square bracket bytes happen to fall in the designated range.
+	test $(git diff --cached --name-only --diff-filter=A -z $against |
+	  LC_ALL=C tr -d '[ -~]\0' | wc -c) != 0
+then
+	cat <<\EOF
+Error: Attempt to add a non-ASCII file name.
+
+This can cause problems if you want to work with people on other platforms.
+
+To be portable it is advisable to rename the file.
+
+If you know what you are doing you can disable this check using:
+
+  git config hooks.allownonascii true
+EOF
+	exit 1
+fi
+
+# If there are whitespace errors, print the offending file names and fail.
+exec git diff-index --check --cached $against --

integrations/gitea-repositories-meta/user2/glob.git/hooks/pre-push.sample

@@ -0,0 +1,53 @@
+#!/bin/sh
+
+# An example hook script to verify what is about to be pushed.  Called by "git
+# push" after it has checked the remote status, but before anything has been
+# pushed.  If this script exits with a non-zero status nothing will be pushed.
+#
+# This hook is called with the following parameters:
+#
+# $1 -- Name of the remote to which the push is being done
+# $2 -- URL to which the push is being done
+#
+# If pushing without using a named remote those arguments will be equal.
+#
+# Information about the commits which are being pushed is supplied as lines to
+# the standard input in the form:
+#
+#   <local ref> <local sha1> <remote ref> <remote sha1>
+#
+# This sample shows how to prevent push of commits where the log message starts
+# with "WIP" (work in progress).
+
+remote="$1"
+url="$2"
+
+z40=0000000000000000000000000000000000000000
+
+while read local_ref local_sha remote_ref remote_sha
+do
+	if [ "$local_sha" = $z40 ]
+	then
+		# Handle delete
+		:
+	else
+		if [ "$remote_sha" = $z40 ]
+		then
+			# New branch, examine all commits
+			range="$local_sha"
+		else
+			# Update to existing branch, examine new commits
+			range="$remote_sha..$local_sha"
+		fi
+
+		# Check for WIP commit
+		commit=`git rev-list -n 1 --grep '^WIP' "$range"`
+		if [ -n "$commit" ]
+		then
+			echo >&2 "Found WIP commit in $local_ref, not pushing"
+			exit 1
+		fi
+	fi
+done
+
+exit 0

integrations/gitea-repositories-meta/user2/glob.git/hooks/pre-rebase.sample

@@ -0,0 +1,169 @@
+#!/bin/sh
+#
+# Copyright (c) 2006, 2008 Junio C Hamano
+#
+# The "pre-rebase" hook is run just before "git rebase" starts doing
+# its job, and can prevent the command from running by exiting with
+# non-zero status.
+#
+# The hook is called with the following parameters:
+#
+# $1 -- the upstream the series was forked from.
+# $2 -- the branch being rebased (or empty when rebasing the current branch).
+#
+# This sample shows how to prevent topic branches that are already
+# merged to 'next' branch from getting rebased, because allowing it
+# would result in rebasing already published history.
+
+publish=next
+basebranch="$1"
+if test "$#" = 2
+then
+	topic="refs/heads/$2"
+else
+	topic=`git symbolic-ref HEAD` ||
+	exit 0 ;# we do not interrupt rebasing detached HEAD
+fi
+
+case "$topic" in
+refs/heads/??/*)
+	;;
+*)
+	exit 0 ;# we do not interrupt others.
+	;;
+esac
+
+# Now we are dealing with a topic branch being rebased
+# on top of master.  Is it OK to rebase it?
+
+# Does the topic really exist?
+git show-ref -q "$topic" || {
+	echo >&2 "No such branch $topic"
+	exit 1
+}
+
+# Is topic fully merged to master?
+not_in_master=`git rev-list --pretty=oneline ^master "$topic"`
+if test -z "$not_in_master"
+then
+	echo >&2 "$topic is fully merged to master; better remove it."
+	exit 1 ;# we could allow it, but there is no point.
+fi
+
+# Is topic ever merged to next?  If so you should not be rebasing it.
+only_next_1=`git rev-list ^master "^$topic" ${publish} | sort`
+only_next_2=`git rev-list ^master           ${publish} | sort`
+if test "$only_next_1" = "$only_next_2"
+then
+	not_in_topic=`git rev-list "^$topic" master`
+	if test -z "$not_in_topic"
+	then
+		echo >&2 "$topic is already up to date with master"
+		exit 1 ;# we could allow it, but there is no point.
+	else
+		exit 0
+	fi
+else
+	not_in_next=`git rev-list --pretty=oneline ^${publish} "$topic"`
+	/usr/bin/perl -e '
+		my $topic = $ARGV[0];
+		my $msg = "* $topic has commits already merged to public branch:\n";
+		my (%not_in_next) = map {
+			/^([0-9a-f]+) /;
+			($1 => 1);
+		} split(/\n/, $ARGV[1]);
+		for my $elem (map {
+				/^([0-9a-f]+) (.*)$/;
+				[$1 => $2];
+			} split(/\n/, $ARGV[2])) {
+			if (!exists $not_in_next{$elem->[0]}) {
+				if ($msg) {
+					print STDERR $msg;
+					undef $msg;
+				}
+				print STDERR " $elem->[1]\n";
+			}
+		}
+	' "$topic" "$not_in_next" "$not_in_master"
+	exit 1
+fi
+
+<<\DOC_END
+
+This sample hook safeguards topic branches that have been
+published from being rewound.
+
+The workflow assumed here is:
+
+ * Once a topic branch forks from "master", "master" is never
+   merged into it again (either directly or indirectly).
+
+ * Once a topic branch is fully cooked and merged into "master",
+   it is deleted.  If you need to build on top of it to correct
+   earlier mistakes, a new topic branch is created by forking at
+   the tip of the "master".  This is not strictly necessary, but
+   it makes it easier to keep your history simple.
+
+ * Whenever you need to test or publish your changes to topic
+   branches, merge them into "next" branch.
+
+The script, being an example, hardcodes the publish branch name
+to be "next", but it is trivial to make it configurable via
+$GIT_DIR/config mechanism.
+
+With this workflow, you would want to know:
+
+(1) ... if a topic branch has ever been merged to "next".  Young
+    topic branches can have stupid mistakes you would rather
+    clean up before publishing, and things that have not been
+    merged into other branches can be easily rebased without
+    affecting other people.  But once it is published, you would
+    not want to rewind it.
+
+(2) ... if a topic branch has been fully merged to "master".
+    Then you can delete it.  More importantly, you should not
+    build on top of it -- other people may already want to
+    change things related to the topic as patches against your
+    "master", so if you need further changes, it is better to
+    fork the topic (perhaps with the same name) afresh from the
+    tip of "master".
+
+Let's look at this example:
+
+		   o---o---o---o---o---o---o---o---o---o "next"
+		  /       /           /           /
+		 /   a---a---b A     /           /
+		/   /               /           /
+	       /   /   c---c---c---c B         /
+	      /   /   /             \         /
+	     /   /   /   b---b C     \       /
+	    /   /   /   /             \     /
+    ---o---o---o---o---o---o---o---o---o---o---o "master"
+
+
+A, B and C are topic branches.
+
+ * A has one fix since it was merged up to "next".
+
+ * B has finished.  It has been fully merged up to "master" and "next",
+   and is ready to be deleted.
+
+ * C has not merged to "next" at all.
+
+We would want to allow C to be rebased, refuse A, and encourage
+B to be deleted.
+
+To compute (1):
+
+	git rev-list ^master ^topic next
+	git rev-list ^master        next
+
+	if these match, topic has not merged in next at all.
+
+To compute (2):
+
+	git rev-list master..topic
+
+	if this is empty, it is fully merged to "master".
+
+DOC_END

integrations/gitea-repositories-meta/user2/glob.git/hooks/pre-receive.sample

@@ -0,0 +1,24 @@
+#!/bin/sh
+#
+# An example hook script to make use of push options.
+# The example simply echoes all push options that start with 'echoback='
+# and rejects all pushes when the "reject" push option is used.
+#
+# To enable this hook, rename this file to "pre-receive".
+
+if test -n "$GIT_PUSH_OPTION_COUNT"
+then
+	i=0
+	while test "$i" -lt "$GIT_PUSH_OPTION_COUNT"
+	do
+		eval "value=\$GIT_PUSH_OPTION_$i"
+		case "$value" in
+		echoback=*)
+			echo "echo from the pre-receive-hook: ${value#*=}" >&2
+			;;
+		reject)
+			exit 1
+		esac
+		i=$((i + 1))
+	done
+fi

integrations/gitea-repositories-meta/user2/glob.git/hooks/prepare-commit-msg.sample

@@ -0,0 +1,42 @@
+#!/bin/sh
+#
+# An example hook script to prepare the commit log message.
+# Called by "git commit" with the name of the file that has the
+# commit message, followed by the description of the commit
+# message's source.  The hook's purpose is to edit the commit
+# message file.  If the hook fails with a non-zero status,
+# the commit is aborted.
+#
+# To enable this hook, rename this file to "prepare-commit-msg".
+
+# This hook includes three examples. The first one removes the
+# "# Please enter the commit message..." help message.
+#
+# The second includes the output of "git diff --name-status -r"
+# into the message, just before the "git status" output.  It is
+# commented because it doesn't cope with --amend or with squashed
+# commits.
+#
+# The third example adds a Signed-off-by line to the message, that can
+# still be edited.  This is rarely a good idea.
+
+COMMIT_MSG_FILE=$1
+COMMIT_SOURCE=$2
+SHA1=$3
+
+/usr/bin/perl -i.bak -ne 'print unless(m/^. Please enter the commit message/..m/^#$/)' "$COMMIT_MSG_FILE"
+
+# case "$COMMIT_SOURCE,$SHA1" in
+#  ,|template,)
+#    /usr/bin/perl -i.bak -pe '
+#       print "\n" . `git diff --cached --name-status -r`
+# 	 if /^#/ && $first++ == 0' "$COMMIT_MSG_FILE" ;;
+#  *) ;;
+# esac
+
+# SOB=$(git var GIT_COMMITTER_IDENT | sed -n 's/^\(.*>\).*$/Signed-off-by: \1/p')
+# git interpret-trailers --in-place --trailer "$SOB" "$COMMIT_MSG_FILE"
+# if test -z "$COMMIT_SOURCE"
+# then
+#   /usr/bin/perl -i.bak -pe 'print "\n" if !$first_line++' "$COMMIT_MSG_FILE"
+# fi

integrations/gitea-repositories-meta/user2/glob.git/hooks/update.sample

@@ -0,0 +1,128 @@
+#!/bin/sh
+#
+# An example hook script to block unannotated tags from entering.
+# Called by "git receive-pack" with arguments: refname sha1-old sha1-new
+#
+# To enable this hook, rename this file to "update".
+#
+# Config
+# ------
+# hooks.allowunannotated
+#   This boolean sets whether unannotated tags will be allowed into the
+#   repository.  By default they won't be.
+# hooks.allowdeletetag
+#   This boolean sets whether deleting tags will be allowed in the
+#   repository.  By default they won't be.
+# hooks.allowmodifytag
+#   This boolean sets whether a tag may be modified after creation. By default
+#   it won't be.
+# hooks.allowdeletebranch
+#   This boolean sets whether deleting branches will be allowed in the
+#   repository.  By default they won't be.
+# hooks.denycreatebranch
+#   This boolean sets whether remotely creating branches will be denied
+#   in the repository.  By default this is allowed.
+#
+
+# --- Command line
+refname="$1"
+oldrev="$2"
+newrev="$3"
+
+# --- Safety check
+if [ -z "$GIT_DIR" ]; then
+	echo "Don't run this script from the command line." >&2
+	echo " (if you want, you could supply GIT_DIR then run" >&2
+	echo "  $0 <ref> <oldrev> <newrev>)" >&2
+	exit 1
+fi
+
+if [ -z "$refname" -o -z "$oldrev" -o -z "$newrev" ]; then
+	echo "usage: $0 <ref> <oldrev> <newrev>" >&2
+	exit 1
+fi
+
+# --- Config
+allowunannotated=$(git config --bool hooks.allowunannotated)
+allowdeletebranch=$(git config --bool hooks.allowdeletebranch)
+denycreatebranch=$(git config --bool hooks.denycreatebranch)
+allowdeletetag=$(git config --bool hooks.allowdeletetag)
+allowmodifytag=$(git config --bool hooks.allowmodifytag)
+
+# check for no description
+projectdesc=$(sed -e '1q' "$GIT_DIR/description")
+case "$projectdesc" in
+"Unnamed repository"* | "")
+	echo "*** Project description file hasn't been set" >&2
+	exit 1
+	;;
+esac
+
+# --- Check types
+# if $newrev is 0000...0000, it's a commit to delete a ref.
+zero="0000000000000000000000000000000000000000"
+if [ "$newrev" = "$zero" ]; then
+	newrev_type=delete
+else
+	newrev_type=$(git cat-file -t $newrev)
+fi
+
+case "$refname","$newrev_type" in
+	refs/tags/*,commit)
+		# un-annotated tag
+		short_refname=${refname##refs/tags/}
+		if [ "$allowunannotated" != "true" ]; then
+			echo "*** The un-annotated tag, $short_refname, is not allowed in this repository" >&2
+			echo "*** Use 'git tag [ -a | -s ]' for tags you want to propagate." >&2
+			exit 1
+		fi
+		;;
+	refs/tags/*,delete)
+		# delete tag
+		if [ "$allowdeletetag" != "true" ]; then
+			echo "*** Deleting a tag is not allowed in this repository" >&2
+			exit 1
+		fi
+		;;
+	refs/tags/*,tag)
+		# annotated tag
+		if [ "$allowmodifytag" != "true" ] && git rev-parse $refname > /dev/null 2>&1
+		then
+			echo "*** Tag '$refname' already exists." >&2
+			echo "*** Modifying a tag is not allowed in this repository." >&2
+			exit 1
+		fi
+		;;
+	refs/heads/*,commit)
+		# branch
+		if [ "$oldrev" = "$zero" -a "$denycreatebranch" = "true" ]; then
+			echo "*** Creating a branch is not allowed in this repository" >&2
+			exit 1
+		fi
+		;;
+	refs/heads/*,delete)
+		# delete branch
+		if [ "$allowdeletebranch" != "true" ]; then
+			echo "*** Deleting a branch is not allowed in this repository" >&2
+			exit 1
+		fi
+		;;
+	refs/remotes/*,commit)
+		# tracking branch
+		;;
+	refs/remotes/*,delete)
+		# delete tracking branch
+		if [ "$allowdeletebranch" != "true" ]; then
+			echo "*** Deleting a tracking branch is not allowed in this repository" >&2
+			exit 1
+		fi
+		;;
+	*)
+		# Anything else (is there anything else?)
+		echo "*** Update hook: unknown type of update to ref $refname of type $newrev_type" >&2
+		exit 1
+		;;
+esac
+
+# --- Finished
+exit 0

integrations/gitea-repositories-meta/user2/glob.git/info/exclude

@@ -0,0 +1,6 @@
+# git ls-files --others --exclude-from=.git/info/exclude
+# Lines that start with '#' are comments.
+# For a project mostly in C, the following would be a good set of
+# exclude patterns (uncomment them if you want to use them):
+# *.[oa]
+# *~

integrations/gitea-repositories-meta/user2/glob.git/objects/c8/eb3b6c767ccb68411d0a1f6c769be69fb4d95a

@@ -0,0 +1 @@
+x
+)JMU03d040031QHÒ+©(a¨é:ô㆖ÜÖo«Þ<KšÿQ@ô§Ü P¨dè‹ÔKÎU_#â?éû¿ãd™½¯"}
•‡

integrations/gitea-repositories-meta/user2/glob.git/objects/ef/6b814b610d8e7717aa0f71fbe5842bcf814697

@@ -0,0 +1,2 @@
+x
­О9В0@Qjџb.@д8“MB*Z®аxЖБВЋ#/·'вґЇшъ&†а
+(ХћJbНФZЛ¤Р�ОШy™$Оrњ{ћжОhЖ…€†	…®е<ЄућS€рLz#—х'»zЯjж”›-&Юэ§Y]yХҐ11\Ўн‡q@D…p–ќ”вРcЈрЯ‚вN…s
л<gсїЋK©

integrations/gitea-repositories-meta/user2/glob.git/refs/heads/master

@@ -0,0 +1 @@
+ef6b814b610d8e7717aa0f71fbe5842bcf814697

integrations/repo_search_test.go

@@ -10,6 +10,7 @@ import (
 	"time"
 
 	"code.gitea.io/gitea/models"
+	"code.gitea.io/gitea/modules/setting"
 
 	"github.com/PuerkitoBio/goquery"
 	"github.com/stretchr/testify/assert"
@@ -33,19 +34,41 @@ func TestSearchRepo(t *testing.T) {
 	repo, err := models.GetRepositoryByOwnerAndName("user2", "repo1")
 	assert.NoError(t, err)
 
+	executeIndexer(t, repo, models.UpdateRepoIndexer)
+
+	testSearch(t, "/user2/repo1/search?q=Description&page=1", []string{"README.md"})
+
+	setting.Indexer.IncludePatterns = setting.IndexerGlobFromString("**.txt")
+	setting.Indexer.ExcludePatterns = setting.IndexerGlobFromString("**/y/**")
+
+	repo, err = models.GetRepositoryByOwnerAndName("user2", "glob")
+	assert.NoError(t, err)
+
+	executeIndexer(t, repo, models.DeleteRepoFromIndexer)
+	executeIndexer(t, repo, models.UpdateRepoIndexer)
+
+	testSearch(t, "/user2/glob/search?q=loren&page=1", []string{"a.txt"})
+	testSearch(t, "/user2/glob/search?q=file3&page=1", []string{"x/b.txt"})
+	testSearch(t, "/user2/glob/search?q=file4&page=1", []string{})
+	testSearch(t, "/user2/glob/search?q=file5&page=1", []string{})
+}
+
+func testSearch(t *testing.T, url string, expected []string) {
+	req := NewRequestf(t, "GET", url)
+	resp := MakeRequest(t, req, http.StatusOK)
+
+	filenames := resultFilenames(t, NewHTMLParser(t, resp.Body))
+	assert.EqualValues(t, expected, filenames)
+}
+
+func executeIndexer(t *testing.T, repo *models.Repository, op func(*models.Repository, ...chan<- error)) {
 	waiter := make(chan error, 1)
-	models.UpdateRepoIndexer(repo, waiter)
+	op(repo, waiter)
 
 	select {
 	case err := <-waiter:
 		assert.NoError(t, err)
 	case <-time.After(1 * time.Minute):
-		assert.Fail(t, "UpdateRepoIndexer took too long")
+		assert.Fail(t, "Repository indexer took too long")
 	}
-
-	req := NewRequestf(t, "GET", "/user2/repo1/search?q=Description&page=1")
-	resp := MakeRequest(t, req, http.StatusOK)
-
-	filenames := resultFilenames(t, NewHTMLParser(t, resp.Body))
-	assert.EqualValues(t, []string{"README.md"}, filenames)
 }

models/fixtures/repo_unit.yml

@@ -402,4 +402,39 @@
   repo_id: 11
   type: 1
   config: "{}"
-  created_unix: 946684810
+  created_unix: 946684810
+
+-
+  id: 59
+  repo_id: 42
+  type: 1
+  config: "{}"
+  created_unix: 946684810
+
+-
+  id: 60
+  repo_id: 42
+  type: 4
+  config: "{}"
+  created_unix: 946684810
+
+-
+  id: 61
+  repo_id: 42
+  type: 5
+  config: "{}"
+  created_unix: 946684810
+
+-
+  id: 62
+  repo_id: 42
+  type: 2
+  config: "{\"EnableTimetracker\":true,\"AllowOnlyContributorsToTrackTime\":true}"
+  created_unix: 946684810
+
+-
+  id: 63
+  repo_id: 42
+  type: 3
+  config: "{\"IgnoreWhitespaceConflicts\":false,\"AllowMerge\":true,\"AllowRebase\":true,\"AllowRebaseMerge\":true,\"AllowSquash\":true}"
+  created_unix: 946684810

models/fixtures/repository.yml

@@ -497,4 +497,15 @@
   num_stars: 0
   num_forks: 0
   num_issues: 0
+  is_mirror: false
+
+-
+  id: 42
+  owner_id: 2
+  lower_name: glob
+  name: glob
+  is_private: false
+  num_stars: 0
+  num_forks: 0
+  num_issues: 0
   is_mirror: false

models/fixtures/user.yml

@@ -30,7 +30,7 @@
   is_admin: false
   avatar: avatar2
   avatar_email: user2@example.com
-  num_repos: 8
+  num_repos: 9
   num_stars: 2
   num_followers: 2
   num_following: 1

models/repo_indexer.go

@@ -234,7 +234,21 @@ func addDelete(filename string, repo *Repository, batch rupture.FlushingBatch) e
 }
 
 func isIndexable(entry *git.TreeEntry) bool {
-	return entry.IsRegular() || entry.IsExecutable()
+	if !entry.IsRegular() && !entry.IsExecutable() {
+		return false
+	}
+	name := strings.ToLower(entry.Name())
+	for _, g := range setting.Indexer.ExcludePatterns {
+		if g.Match(name) {
+			return false
+		}
+	}
+	for _, g := range setting.Indexer.IncludePatterns {
+		if g.Match(name) {
+			return true
+		}
+	}
+	return len(setting.Indexer.IncludePatterns) == 0
 }
 
 // parseGitLsTreeOutput parses the output of a `git ls-tree -r --full-name` command

models/repo_list_test.go

@@ -175,10 +175,10 @@ func TestSearchRepository(t *testing.T) {
 			count: 14},
 		{name: "AllPublic/PublicRepositoriesOfUserIncludingCollaborative",
 			opts:  &SearchRepoOptions{Page: 1, PageSize: 10, OwnerID: 15, AllPublic: true},
-			count: 21},
+			count: 22},
 		{name: "AllPublic/PublicAndPrivateRepositoriesOfUserIncludingCollaborative",
 			opts:  &SearchRepoOptions{Page: 1, PageSize: 10, OwnerID: 15, Private: true, AllPublic: true},
-			count: 27},
+			count: 28},
 		{name: "AllPublic/PublicAndPrivateRepositoriesOfUserIncludingCollaborativeByName",
 			opts:  &SearchRepoOptions{Keyword: "test", Page: 1, PageSize: 10, OwnerID: 15, Private: true, AllPublic: true},
 			count: 15},
@@ -187,7 +187,7 @@ func TestSearchRepository(t *testing.T) {
 			count: 13},
 		{name: "AllPublic/PublicRepositoriesOfOrganization",
 			opts:  &SearchRepoOptions{Page: 1, PageSize: 10, OwnerID: 17, AllPublic: true, Collaborate: util.OptionalBoolFalse},
-			count: 21},
+			count: 22},
 	}
 
 	for _, testCase := range testCases {

modules/setting/indexer.go

@@ -7,6 +7,11 @@ package setting
 import (
 	"path"
 	"path/filepath"
+	"strings"
+
+	"code.gitea.io/gitea/modules/log"
+
+	"github.com/gobwas/glob"
 )
 
 // enumerates all the indexer queue types
@@ -29,6 +34,8 @@ var (
 		IssueQueueDir         string
 		IssueQueueConnStr     string
 		IssueQueueBatchNumber int
+		IncludePatterns       []glob.Glob
+		ExcludePatterns       []glob.Glob
 	}{
 		IssueType:             "bleve",
 		IssuePath:             "indexers/issues.bleve",
@@ -51,6 +58,9 @@ func newIndexerService() {
 	if !filepath.IsAbs(Indexer.RepoPath) {
 		Indexer.RepoPath = path.Join(AppWorkPath, Indexer.RepoPath)
 	}
+	Indexer.IncludePatterns = IndexerGlobFromString(sec.Key("REPO_INDEXER_INCLUDE").MustString(""))
+	Indexer.ExcludePatterns = IndexerGlobFromString(sec.Key("REPO_INDEXER_EXCLUDE").MustString(""))
+
 	Indexer.UpdateQueueLength = sec.Key("UPDATE_BUFFER_LEN").MustInt(20)
 	Indexer.MaxIndexerFileSize = sec.Key("MAX_FILE_SIZE").MustInt64(1024 * 1024)
 	Indexer.IssueQueueType = sec.Key("ISSUE_INDEXER_QUEUE_TYPE").MustString(LevelQueueType)
@@ -58,3 +68,19 @@ func newIndexerService() {
 	Indexer.IssueQueueConnStr = sec.Key("ISSUE_INDEXER_QUEUE_CONN_STR").MustString(path.Join(AppDataPath, ""))
 	Indexer.IssueQueueBatchNumber = sec.Key("ISSUE_INDEXER_QUEUE_BATCH_NUMBER").MustInt(20)
 }
+
+// IndexerGlobFromString parses a comma separated list of patterns and returns a glob.Glob slice suited for repo indexing
+func IndexerGlobFromString(globstr string) []glob.Glob {
+	extarr := make([]glob.Glob, 0, 10)
+	for _, expr := range strings.Split(strings.ToLower(globstr), ",") {
+		expr = strings.TrimSpace(expr)
+		if expr != "" {
+			if g, err := glob.Compile(expr, '.', '/'); err != nil {
+				log.Info("Invalid glob expresion '%s' (skipped): %v", expr, err)
+			} else {
+				extarr = append(extarr, g)
+			}
+		}
+	}
+	return extarr
+}

modules/setting/indexer_test.go

@@ -0,0 +1,73 @@
+// Copyright 2019 The Gitea Authors. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package setting
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+type indexerMatchList struct {
+	value    string
+	position int
+}
+
+func Test_newIndexerGlobSettings(t *testing.T) {
+
+	checkGlobMatch(t, "", []indexerMatchList{})
+	checkGlobMatch(t, "     ", []indexerMatchList{})
+	checkGlobMatch(t, "data, */data, */data/*, **/data/*, **/data/**", []indexerMatchList{
+		{"", -1},
+		{"don't", -1},
+		{"data", 0},
+		{"/data", 1},
+		{"x/data", 1},
+		{"x/data/y", 2},
+		{"a/b/c/data/z", 3},
+		{"a/b/c/data/x/y/z", 4},
+	})
+	checkGlobMatch(t, "*.txt, txt, **.txt, **txt, **txt*", []indexerMatchList{
+		{"my.txt", 0},
+		{"don't", -1},
+		{"mytxt", 3},
+		{"/data/my.txt", 2},
+		{"data/my.txt", 2},
+		{"data/txt", 3},
+		{"data/thistxtfile", 4},
+		{"/data/thistxtfile", 4},
+	})
+	checkGlobMatch(t, "data/**/*.txt, data/**.txt", []indexerMatchList{
+		{"data/a/b/c/d.txt", 0},
+		{"data/a.txt", 1},
+	})
+	checkGlobMatch(t, "**/*.txt, data/**.txt", []indexerMatchList{
+		{"data/a/b/c/d.txt", 0},
+		{"data/a.txt", 0},
+		{"a.txt", -1},
+	})
+}
+
+func checkGlobMatch(t *testing.T, globstr string, list []indexerMatchList) {
+	glist := IndexerGlobFromString(globstr)
+	if len(list) == 0 {
+		assert.Empty(t, glist)
+		return
+	}
+	assert.NotEmpty(t, glist)
+	for _, m := range list {
+		found := false
+		for pos, g := range glist {
+			if g.Match(m.value) {
+				assert.Equal(t, m.position, pos, "Test string `%s` doesn't match `%s`@%d, but matches @%d", m.value, globstr, m.position, pos)
+				found = true
+				break
+			}
+		}
+		if !found {
+			assert.Equal(t, m.position, -1, "Test string `%s` doesn't match `%s` anywhere; expected @%d", m.value, globstr, m.position)
+		}
+	}
+}