[quoted string matcher regexp
tom@zwizwa.be**20111103222621
 Ignore-this: 5810d4640fa3096abe5f22326e59d0f8
] hunk ./lib/x/apachelog-dump.ss 57
-(define (format-sanitize bytes) bytes)
-(define sql-quote "\"")
hunk ./lib/x/apachelog-dump.ss 58
-(define (format-sanitize_ bytes)
-  (let ((bytes (regexp-replace* #"'" bytes "\"")))
-    bytes))
+;(define (format-sanitize_ bytes)
+;  (let ((bytes (regexp-replace* #"'" bytes "\"")))
+;    bytes))
+
+;; Should be ok..
+(define (format-sanitize bytes) bytes)
hunk ./lib/x/apachelog-dump.ss 70
-      (format "~a~a~a"
-              sql-quote
-              (format-sanitize el)
-              sql-quote
-              )
-      )
+      (format "\"~a\"" (format-sanitize el)))
hunk ./lib/x/apachelog-regexp.ss 10
-;; s - quoted string
+;; q - quoted string
hunk ./lib/x/apachelog-regexp.ss 14
+;; w -> 1 value
+;; d -> 7 values
+;; q -> 2 values (2nd one is last matched char in string.  FIXME: how?)
+
+;; Note that the quoted string does not have the outer quotes, but it
+;; does keep escapes inside the string in quoted form.  FIXME: how?
+
hunk ./lib/x/apachelog-regexp.ss 23
-(define q "\"(.*?)\"")
-(define _ "\\s+?")
+
+(define _ "(\\s+?")
+
+;; quoted string (quotes not included)
+; (define q "\"((\\.|[^\\\"])*)\"")    ;; WRONG
+(define q  "\"((\\\\|\\\"|[^\\\"])*)\"")
hunk ./lib/x/apachelog-regexp.ss 92
-
+;; FIXME: the r<x> are due to the double parens in the quoted string matcher.
hunk ./lib/x/apachelog-regexp.ss 106
-                request
+                request r0
hunk ./lib/x/apachelog-regexp.ss 109
-                referrer
-                agent)
+                referrer r1
+                agent r2)
hunk ./lib/x/apachelog-regexp.ss 133
-                request
+                request r1
hunk ./lib/x/apachelog-regexp.ss 136
-                referrer
-                agent)
+                referrer r2
+                agent r3)
hunk ./lib/x/apachelog-regexp.ss 157
-                request
+                request r1
hunk ./lib/x/apachelog-regexp.ss 194
-;(define log (open-input-file "/tmp/access.log"))
-;(define line (read-bytes-line log))
+(define log (open-input-file "/tmp/access.log"))
+(define line (read-bytes-line log))
hunk ./plt.txt 1670
-  escapes correctly.
+  escapes correctly.  see [1]  \"(\\.|[^\"])*\"
hunk ./plt.txt 1672
+[1] http://stackoverflow.com/questions/249791/regex-for-quoted-string-with-escaping-quotes
+
+Entry: Parsing strings
+Date: Thu Nov  3 17:30:17 EDT 2011
+
+All these hacking attempts are really hard to parse!
+
+This one doesn't work for the string matcher:
+
+
+"giebrok.zwizwa.be:80 83.101.57.157 - - [26/Aug/2011:00:18:08 +0200] \"GET /WebID/IISWebAgentIF.dll?postdata=\\\"><script>foo</script> HTTP/1.1\" 302 417 \"-\" \"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)\""
+
+Or in unquoted form:
+giebrok.zwizwa.be:80 83.101.57.157 - - [26/Aug/2011:00:18:08 +0200] "GET /WebID/IISWebAgentIF.dll?postdata=\"><script>foo</script> HTTP/1.1" 302 417 "-" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)"
+
+(define q "\"((\\.|[^\"])*)\"")  ;; quoted string (quotes not included)
+
+Looks like that regexp is wrong, some quoting is missing:
+
+(define q "\"((\\.|[^\\\"])*)\"")