diff options
| author | Jon Dufresne <jon.dufresne@gmail.com> | 2018-12-22 09:28:48 -0800 |
|---|---|---|
| committer | Jon Dufresne <jon.dufresne@gmail.com> | 2018-12-22 13:46:56 -0800 |
| commit | de8326d00dffdb500c02839a98330b869c2457f3 (patch) | |
| tree | 6c5fdae41cf8b335ff1c64f37856786523e4fd0d /examples/httpServerLogParser.py | |
| parent | 59dfd314c23fd653271bdad37631f0497e8ad748 (diff) | |
| download | pyparsing-git-de8326d00dffdb500c02839a98330b869c2457f3.tar.gz | |
Trim trailing white space throughout the project
Many editors clean up trailing white space on save. By removing it all
in one go, it helps keep future diffs cleaner by avoiding spurious white
space changes on unrelated lines.
Diffstat (limited to 'examples/httpServerLogParser.py')
| -rw-r--r-- | examples/httpServerLogParser.py | 28 |
1 files changed, 14 insertions, 14 deletions
diff --git a/examples/httpServerLogParser.py b/examples/httpServerLogParser.py index a147a05..261cea3 100644 --- a/examples/httpServerLogParser.py +++ b/examples/httpServerLogParser.py @@ -5,11 +5,11 @@ """
Parser for HTTP server log output, of the form:
-195.146.134.15 - - [20/Jan/2003:08:55:36 -0800]
-"GET /path/to/page.html HTTP/1.0" 200 4649 "http://www.somedomain.com/020602/page.html"
+195.146.134.15 - - [20/Jan/2003:08:55:36 -0800]
+"GET /path/to/page.html HTTP/1.0" 200 4649 "http://www.somedomain.com/020602/page.html"
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)"
-127.0.0.1 - u.surname@domain.com [12/Sep/2006:14:13:53 +0300]
-"GET /skins/monobook/external.png HTTP/1.0" 304 - "http://wiki.mysite.com/skins/monobook/main.css"
+127.0.0.1 - u.surname@domain.com [12/Sep/2006:14:13:53 +0300]
+"GET /skins/monobook/external.png HTTP/1.0" 304 - "http://wiki.mysite.com/skins/monobook/main.css"
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.0.6) Gecko/20060728 Firefox/1.5.0.6"
You can then break it up as follows:
@@ -32,30 +32,30 @@ def getCmdFields( s, l, t ): logLineBNF = None
def getLogLineBNF():
global logLineBNF
-
+
if logLineBNF is None:
integer = Word( nums )
ipAddress = delimitedList( integer, ".", combine=True )
-
+
timeZoneOffset = Word("+-",nums)
month = Word(string.uppercase, string.lowercase, exact=3)
- serverDateTime = Group( Suppress("[") +
+ serverDateTime = Group( Suppress("[") +
Combine( integer + "/" + month + "/" + integer +
":" + integer + ":" + integer + ":" + integer ) +
- timeZoneOffset +
+ timeZoneOffset +
Suppress("]") )
-
- logLineBNF = ( ipAddress.setResultsName("ipAddr") +
+
+ logLineBNF = ( ipAddress.setResultsName("ipAddr") +
Suppress("-") +
("-" | Word( alphas+nums+"@._" )).setResultsName("auth") +
- serverDateTime.setResultsName("timestamp") +
+ serverDateTime.setResultsName("timestamp") +
dblQuotedString.setResultsName("cmd").setParseAction(getCmdFields) +
- (integer | "-").setResultsName("statusCode") +
- (integer | "-").setResultsName("numBytesSent") +
+ (integer | "-").setResultsName("statusCode") +
+ (integer | "-").setResultsName("numBytesSent") +
dblQuotedString.setResultsName("referrer").setParseAction(removeQuotes) +
dblQuotedString.setResultsName("clientSfw").setParseAction(removeQuotes) )
return logLineBNF
-
+
testdata = """
195.146.134.15 - - [20/Jan/2003:08:55:36 -0800] "GET /path/to/page.html HTTP/1.0" 200 4649 "http://www.somedomain.com/020602/page.html" "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)"
111.111.111.11 - - [16/Feb/2004:04:09:49 -0800] "GET /ads/redirectads/336x280redirect.htm HTTP/1.1" 304 - "http://www.foobarp.org/theme_detail.php?type=vs&cat=0&mid=27512" "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)"
|