Add testing support for selectively ignoring regex patterns. First use case is to ignore datestamps for page creation. Also add ignore:date to the spec. in urltest.list for agenda and meeting pages, and add some ignore date regex patterns.

 - Legacy-Id: 542

Author: levkowetz

ietf/meeting/testurl.list

@@ -1,5 +1,5 @@
-200	/meeting/68/agenda.html		https://datatracker.ietf.org/public/meeting_agenda_html.cgi?meeting_num=68
-200	/meeting/68/agenda.txt		https://datatracker.ietf.org/public/meeting_agenda_text.cgi?meeting_num=68
-200	/meeting/69/materials.html	https://datatracker.ietf.org/public/meeting_materials.cgi?meeting_num=69
-404	/meeting/70/agenda.html
-404	/meeting/70/materials.html
+200,ignore:date	/meeting/68/agenda.html		https://datatracker.ietf.org/public/meeting_agenda_html.cgi?meeting_num=68
+200,ignore:date	/meeting/68/agenda.txt		https://datatracker.ietf.org/public/meeting_agenda_text.cgi?meeting_num=68
+200,ignore:date	/meeting/69/materials.html	https://datatracker.ietf.org/public/meeting_materials.cgi?meeting_num=69
+404		/meeting/70/agenda.html
+404		/meeting/70/materials.html

ietf/tests.py

@@ -32,11 +32,17 @@ def reduce_text(html, pre=False, fill=True):
     text = text.replace(" : ", ": ").replace(" :", ": ")
     text = text.replace('."', '".')
     text = text.replace(',"', '",')
+    return text
+
+def lines(text, pre=False):
     if pre:
         text = text.split("\n")
     else:
         text = [ line.strip() for line in text.split("\n") if line.strip()]
-    return text
+    
+def sorted(lst):
+    lst.sort()
+    return lst
 
 def get_patterns(module):
     all = []
@@ -81,7 +87,10 @@ def read_testurls(filename):
                 codes, testurl, goodurl = urlspec
             else:
                 raise ValueError("Expected 'HTTP_CODE TESTURL [GOODURL]' in %s line, found '%s'." % (filename, line))
-            codes = codes.split(",")
+
+
+            codes = dict([ (item, "") for item in codes.split(",") if not":" in item] +
+                         [ (item.split(":")[:2]) for item in codes.split(",") if ":" in item] )
             tuples += [ (codes, testurl, goodurl) ]
     file.close()
     return tuples
@@ -119,6 +128,7 @@ def module_setup(module):
     module.testtuples = []
     module.testurls = []
     module.diffchunks = []
+    module.ignores = {}
     module.testtuples = get_testurls()
     module.testurls = [ tuple[1] for tuple in module.testtuples ]
 
@@ -131,10 +141,19 @@ def module_setup(module):
             chunk = re.sub(r"([\[\]().|+*?])", r"\\\1", chunk)
             # @@ -27,0 \+23,1 @@
             chunk = re.sub(r"(?m)^@@ -\d+,(\d+) \\\+\d+,(\d+) @@$", r"@@ -\d+,\1 \+\d+,\2 @@", chunk)
-            #print "*** Installing diff chunk:"
-            #print chunk
             module.diffchunks.append(chunk)
 
+    # find ignore chunks
+    for root, dirs, files in os.walk(settings.BASE_DIR+"/../test/ignore/"):
+        # This only expects one directory level below test/ignore/:
+        for file in files:
+            path = root + "/" + file
+            dir = root.split("/")[-1]
+            chunk = filetext(path).strip()
+            if not dir in module.ignores:
+                module.ignores[dir] = []
+            module.ignores[dir].append(chunk)
+
     # extract application urls:
     module.patterns = get_patterns(ietf.urls)
 
@@ -273,28 +292,34 @@ def doUrlsTest(self, lst):
                     try:
                         if goodhtml and response.content:
                             if "sort" in codes:
-                                def sorted(l):
-                                    l.sort()
-                                    return l
-                                testtext = sorted(reduce_text(response.content, fill=False))
+                                testtext = reduce_text(response.content, fill=False)
+                                goodtext = reduce_text(goodhtml, fill=False)
+                            else:
+                                testtext = reduce_text(response.content)
+                                goodtext = reduce_text(goodhtml)
+                            if "ignore" in codes:
+                                ignores = codes["ignore"].split("/")
+                                for ignore in ignores:
+                                    for regex in module.ignores[ignore]:
+                                        testtext = re.sub(regex, "", testtext)
+                                        goodtext = re.sub(regex, "", goodtext)
+                            testtext = lines(testtext)
+                            goodtext = lines(goodtext)
+                            if "sort" in codes:
+                                testtext = sorted(testtext)
                                 while testtext and not testtext[0]:
                                     del testtext[0]
-                                goodtext = sorted(reduce_text(goodhtml, fill=False))
+                                goodtext = sorted(goodtext)
                                 while goodtext and not goodtext[0]:
                                     del goodtext[0]
-                            else:
-                                testtext = reduce_text(response.content)
-                                goodtext = reduce_text(goodhtml)
                             if testtext == goodtext:
                                 note("OK   cmp %s" % (url))
                             else:
                                 contextlines = 0
                                 difflist = list(unified_diff(goodtext, testtext, master, url, "", "", contextlines, lineterm=""))
                                 diff = "\n".join(difflist)
                                 for chunk in module.diffchunks:
-                                    #print "*** Checking for chunk:", chunk[:24]
                                     while re.search(chunk, diff):
-                                        #print "*** Removing chunk of %s lines" % (len(chunk.split("\n")))
                                         diff = re.sub(chunk, "", diff)
                                 if len(diff.strip().splitlines()) == 2:
                                     # only the initial 2 lines of the diff remains --

test/ignore/date/iso-date.regex

@@ -0,0 +1 @@
+20\d\d-\d\d-\d\d \d\d?:\d\d:\d\d( \(\w+\))?

test/ignore/date/mon_day_year_time.regex

@@ -0,0 +1 @@
+(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec) \d\d, [12]0\d\d, \d\d?:\d\d?:\d\d?

test/ignore/date/month_day_year_time.regex

@@ -0,0 +1 @@
+(January|February|March|April|May|June|July|August|September|October|November|December) \d\d, [12]0\d\d, \d\d?:\d\d?:\d\d?