From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00,
	WEIRD_PORT shortcircuit=no autolearn=ham autolearn_force=no
	version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 55EA61F453;
	Thu, 25 Apr 2019 03:19:04 +0000 (UTC)
Date: Thu, 25 Apr 2019 03:19:04 +0000
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH v2] examples: cgit filter for use with WwwHighlight
Message-ID: <20190425031904.GA31675@dcvr>
References: <20190424230214.2378-1-e@80x24.org>
 <20190424230214.2378-5-e@80x24.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20190424230214.2378-5-e@80x24.org>
List-Id: <meta.public-inbox.org>

I'm using this as the cgit about-filter and source-filter
in https://80x24.org/public-inbox.git
---
 v2:
 * proper error handling and behavior w.r.t. large files
 * do not send Expect: header (and waiting for 100-continue)
 * correctly distinguish between about-filter and source-filter
   (v1 was creating nested <pre> when used as source-filter)

 interdiff:
 $ U=https://public-inbox.org/meta
 $ interdiff <(curl -s $U/dafb7a8/s/?b=x.lua) <(curl -s $U/a267d1c/s/?b=x.lua)

 MANIFEST                              |   1 +
 examples/cgit-wwwhighlight-filter.lua | 105 ++++++++++++++++++++++++++
 2 files changed, 106 insertions(+)
 create mode 100644 examples/cgit-wwwhighlight-filter.lua

diff --git a/MANIFEST b/MANIFEST
index 9858b9e..ed8ff49 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -39,6 +39,7 @@ examples/apache2_perl.conf
 examples/apache2_perl_old.conf
 examples/cgi-webrick.rb
 examples/cgit-commit-filter.lua
+examples/cgit-wwwhighlight-filter.lua
 examples/cgit.psgi
 examples/highlight.psgi
 examples/logrotate.conf
diff --git a/examples/cgit-wwwhighlight-filter.lua b/examples/cgit-wwwhighlight-filter.lua
new file mode 100644
index 0000000..a267d1c
--- /dev/null
+++ b/examples/cgit-wwwhighlight-filter.lua
@@ -0,0 +1,105 @@
+-- Copyright (C) 2019 all contributors <meta@public-inbox.org>
+-- License: GPL-2.0+ <https://www.gnu.org/licenses/gpl-2.0.txt>
+--
+-- This filter accesses the PublicInbox::WwwHighlight PSGI endpoint
+-- (see examples/highlight.psgi)
+--
+-- Dependencies: lua-http
+--
+-- disclaimer: written by someone who does not know Lua.
+--
+-- This requires cgit linked with Lua
+-- Usage (in your cgitrc(5) config file):
+--
+--   source-filter=lua:/path/to/this/script.lua
+--   about-filter=lua:/path/to/this/script.lua
+--
+local wwwhighlight_url = 'http://127.0.0.1:9090/'
+local req_timeout = 10
+local too_big = false
+
+-- match $PublicInbox::HTTP::MAX_REQUEST_BUFFER
+local max_len = 10 * 1024 * 1024
+
+-- about-filter needs surrounding <pre> tags if all we do is
+-- highlight and linkify
+local pre = true
+
+function filter_open(...)
+	req_body = ""
+
+	-- detect when we're used in an about-filter
+	local repo_url = os.getenv('CGIT_REPO_URL')
+	if repo_url then
+		local path_info = os.getenv('PATH_INFO')
+		rurl = path_info:match("^/(.+)/about/?$")
+		pre = rurl == repo_url
+	end
+
+	-- hand filename off for language detection
+	local fn = select(1, ...)
+	if fn then
+		local http_util = require 'http.util'
+		wwwhighlight_url = wwwhighlight_url .. http_util.encodeURI(fn)
+	end
+end
+
+-- try to buffer the entire source in memory
+function filter_write(str)
+	if too_big then
+		html(str)
+	elseif (req_body:len() + str:len()) > max_len then
+		too_big = true
+		req_body = ""
+		html(req_body)
+		html(str)
+	else
+		req_body = req_body .. str
+	end
+end
+
+function fail(err)
+	io.stderr:write(tostring(err), "\n")
+	if pre then
+		html("<pre>")
+	end
+	html_txt(req_body)
+	if pre then
+		html("</pre>")
+	end
+	return 1
+end
+
+function filter_close()
+	if too_big then
+		return 0
+	end
+	local request = require 'http.request'
+	local req = request.new_from_uri(wwwhighlight_url)
+	req.headers:upsert(':method', 'PUT')
+	req:set_body(req_body)
+
+	-- don't wait for 100-Continue message from the PSGI app
+	req.headers:delete('expect')
+
+	local headers, stream = req:go(req_timeout)
+	if headers == nil then
+		return fail(stream)
+	end
+	local status = headers:get(':status')
+	if status ~= '200' then
+		return fail('status ' .. status)
+	end
+	local body, err = stream:get_body_as_string()
+	if not body and err then
+		return fail(err)
+	end
+	if pre then
+		html("<pre>")
+	end
+	html(body)
+	if pre then
+		html("</pre>")
+	end
+	return 0
+end
-- 
EW