[PATCH] Add log-format variable %HQ, to log HTTP query strings

[Andrew Hayworth]

Since this came up in another thread, it seems reasonable to add a
patch that implements %HQ as a log-format variable to record the HTTP
query string. Leaving the initial '?' is intentional, but I don't feel
strongly one way or another.

-- 
- Andrew Hayworth


>From b87770d5e513fc923d0d94d2b1d0de00d88acb98 Mon Sep 17 00:00:00 2001
From: Andrew Hayworth <andrew.haywo...@getbraintree.com>
Date: Fri, 31 Jul 2015 16:14:16 +0000
Subject: [PATCH 1/1] Add log-format variable %HQ, to log HTTP query strings

Since sample fetches are not always available in the response phase,
this patch implements %HQ such that:

  GET /foo?bar=baz HTTP/1.0

...would be logged as:

  ?bar=baz
---
 doc/configuration.txt |  1 +
 include/types/log.h   |  1 +
 src/log.c             | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

diff --git a/doc/configuration.txt b/doc/configuration.txt
index db97cc7..b3ba8a0 100644
--- a/doc/configuration.txt
+++ b/doc/configuration.txt
@@ -13987,6 +13987,7 @@ Please refer to the table below for currently
defined variables :
   |   | %H   | hostname                                      | string      |
   | H | %HM  | HTTP method (ex: POST)                        | string      |
   | H | %HP  | HTTP request URI without query string (path)  | string      |
+  | H | %HQ  | HTTP request URI query string (ex: ?bar=baz)  | string      |
   | H | %HU  | HTTP request URI (ex: /foo?bar=baz)           | string      |
   | H | %HV  | HTTP version (ex: HTTP/1.0)                   | string      |
   |   | %ID  | unique-id                                     | string      |
diff --git a/include/types/log.h b/include/types/log.h
index bbfe020..d0fb966 100644
--- a/include/types/log.h
+++ b/include/types/log.h
@@ -96,6 +96,7 @@ enum {
  LOG_FMT_HTTP_METHOD,
  LOG_FMT_HTTP_URI,
  LOG_FMT_HTTP_PATH,
+ LOG_FMT_HTTP_QUERY,
  LOG_FMT_HTTP_VERSION,
  LOG_FMT_HOSTNAME,
  LOG_FMT_UNIQUEID,
diff --git a/src/log.c b/src/log.c
index ffd8f10..1112f8a 100644
--- a/src/log.c
+++ b/src/log.c
@@ -111,6 +111,7 @@ static const struct logformat_type logformat_keywords[] = {
  { "hsl", LOG_FMT_HDRRESPONSLIST, PR_MODE_TCP, LW_RSPHDR, NULL },  /*
header response list */
  { "HM", LOG_FMT_HTTP_METHOD, PR_MODE_HTTP, LW_REQ, NULL },  /* HTTP method */
  { "HP", LOG_FMT_HTTP_PATH, PR_MODE_HTTP, LW_REQ, NULL },  /* HTTP path */
+ { "HQ", LOG_FMT_HTTP_QUERY, PR_MODE_HTTP, LW_REQ, NULL },  /* HTTP query */
  { "HU", LOG_FMT_HTTP_URI, PR_MODE_HTTP, LW_REQ, NULL },  /* HTTP full URI */
  { "HV", LOG_FMT_HTTP_VERSION, PR_MODE_HTTP, LW_REQ, NULL },  /* HTTP
version */
  { "lc", LOG_FMT_LOGCNT, PR_MODE_TCP, LW_INIT, NULL }, /* log counter */
@@ -937,6 +938,7 @@ int build_logline(struct stream *s, char *dst,
size_t maxsize, struct list *list
  struct chunk chunk;
  char *uri;
  char *spc;
+ char *qmark;
  char *end;
  struct tm tm;
  int t_request;
@@ -1578,6 +1580,42 @@ int build_logline(struct stream *s, char *dst,
size_t maxsize, struct list *list
        last_isspace = 0;
        break;

+     case LOG_FMT_HTTP_QUERY: // %HQ
+       uri = txn->uri ? txn->uri : "<BADREQ>";
+
+       if (tmp->options & LOG_OPT_QUOTE)
+         LOGCHAR('"');
+
+       end = uri + strlen(uri);
+       // look for the first question mark
+       while (uri < end && *uri != '?')
+         uri++;
+
+       qmark = uri;
+
+       // look for first space or question mark after url
+       while (uri < end && !HTTP_IS_SPHT(*uri))
+         uri++;
+
+       if (!txn->uri) {
+         chunk.str = "<BADREQ>";
+         chunk.len = strlen("<BADREQ>");
+       } else {
+         chunk.str = qmark;
+         chunk.len = uri - qmark;
+       }
+
+       ret = encode_chunk(tmplog, dst + maxsize, '#', url_encode_map, &chunk);
+       if (ret == NULL || *ret != '\0')
+         goto out;
+
+       tmplog = ret;
+       if (tmp->options & LOG_OPT_QUOTE)
+         LOGCHAR('"');
+
+       last_isspace = 0;
+       break;
+
      case LOG_FMT_HTTP_URI: // %HU
        uri = txn->uri ? txn->uri : "<BADREQ>";

--
2.1.3

0001-Add-log-format-variable-HQ-to-log-HTTP-query-strings.patch
Description: Binary data