Attempt to fix localhtmlvalidate

It was already broken and didn't work properly, but update to py3 and at
least make it run. More changes are necessary to actually make it happy
again.

diff --git a/tools/localhtmlvalidate/localhtmlvalidate.py b/tools/localhtmlvalidate/localhtmlvalidate.py
index 348693720db32da5497460e44edffdc042feaeba..4332350bf78f18e45cfeda5e944a05accd917580 100755 (executable)
--- a/tools/localhtmlvalidate/localhtmlvalidate.py
+++ b/tools/localhtmlvalidate/localhtmlvalidate.py
@@ -14,31 +14,9 @@
 #
 
 import sys
-import urllib
-import httplib
+import requests
 import re
-import HTMLParser
-
-BOUNDARY = "-=--=foobar-=--="
-
-
-def encode_multipart_formdata(fields, files):
-    L = []
-    for (key, value) in fields:
-        L.append('--' + BOUNDARY)
-        L.append('Content-Disposition: form-data; name="%s"' % key)
-        L.append('')
-        L.append(value)
-    for (key, filename, value) in files:
-        L.append('--' + BOUNDARY)
-        L.append('Content-Disposition: form-data; name="%s"; filename="%s"' % (key, filename))
-        L.append('Content-Type: text/html')
-        L.append('')
-        L.append(value)
-    L.append('--' + BOUNDARY + '--')
-    L.append('')
-    body = "\r\n".join(L)
-    return body
+import html.parser
 
 
 if __name__ == "__main__":
@@ -46,7 +24,8 @@ if __name__ == "__main__":
         print("Usage: localhtmlvalidate.py <local url>")
         sys.exit(1)
 
-    contents = urllib.urlopen(sys.argv[1]).read()
+    r = requests.get(sys.argv[1])
+    contents = r.text
 
     # Try to figure out where the actual contents start :)
     try:
@@ -55,42 +34,40 @@ if __name__ == "__main__":
         firstline = 0
 
     # Generate a form body
-    body = encode_multipart_formdata(
-        [
-            ('charset', 'utf-8'),
-            ('doctype', 'inline'),
-            ('group', '0'),
-            ('verbose', '1'),
-        ],
-        [('uploaded_file', 'test.html', contents)]
-    )
+    data = {
+        'doctype': 'Inline',
+        'group': '0',
+        'verbose': '1',
+        'prefill': '1',
+        'prefill_doctype': 'html401',
+        'fragment': contents,
+    }
 
     # Now submit it to the w3c validator
-    h = httplib.HTTP("validator.w3.org")
-    h.putrequest("POST", "/check")
-    h.putheader("User-Agent: localcheck-tester/0.0")
-    h.putheader("content-type", "multipart/form-data; boundary=%s" % BOUNDARY)
-    h.putheader("content-length", str(len(body)))
-    h.endheaders()
-    h.send(body)
-    errcode, errmsg, headers = h.getreply()
-    rbody = h.getfile().read()
-    if headers['x-w3c-validator-status'] == 'Valid':
+    resp = requests.post(
+        'https://validator.w3.org/check',
+        data=data,
+        headers={
+            "User-Agent": "localcheck-tester/0.0",
+        },
+        timeout=20,
+    )
+    if resp.headers['x-w3c-validator-status'] == 'Valid':
         print("Page validates!")
         sys.exit(0)
-    elif headers['x-w3c-validator-status'] == 'Invalid':
+    elif resp.headers['x-w3c-validator-status'] == 'Invalid':
         print("Invalid!")
-        print("Errors: %s" % headers['x-w3c-validator-errors'])
-        print("Warnings: %s" % headers['x-w3c-validator-warnings'])
-        hp = HTMLParser.HTMLParser()
-        for m in re.findall('<li class="msg_err">.*?</li>', rbody, re.DOTALL):
-            r = re.search('<em>Line (\d+).*<span class="msg">(.*?)</span>', m, re.DOTALL)
-            print("Line %s (should be around %s): %s" % (r.group(1), int(r.group(1)) - firstline, hp.unescape(r.group(2))))
-
-            r2 = re.search('<code class="input">(.*?)<strong title=".*?">(.*?)</strong>(.*?)</code>', unicode(m, 'utf8'), re.DOTALL)
+        print("Errors: %s" % resp.headers['x-w3c-validator-errors'])
+        print("Warnings: %s" % resp.headers['x-w3c-validator-warnings'])
+        hp = html.parser.HTMLParser()
+        for m in re.findall('<li class="msg_err">.*?</li>', resp.text, re.DOTALL):
+            r = re.search('<em>Line <a href="[^"]+">(\d+)</a>.*<span class="msg">(.*?)</span>', m, re.DOTALL)
+            if r:
+                print("Line %s (should be around %s): %s" % (r.group(1), int(r.group(1)) - firstline, hp.unescape(r.group(2))))
+            r2 = re.search('<code class="input">(.*?)<strong title=".*?">(.*?)</strong>(.*?)</code>', m, re.DOTALL)
             if r2:
                 s = "%s%s%s" % r2.groups()
-                print("Source: %s" % hp.unescape(s).encode('utf-8'))
+                print("Source: %s" % hp.unescape(s))
             print("")
     else:
         print("Unknown status: %s" % headers['x-w3c-validator-status'])