fix: add more HTML validation & fixes (ietf-tools#3891)

* Update vnu.jar

* Fix py2 -> py3 issue

* Run pyupgrade

* test: Add default-jdk to images

* test: Add option to also validate HTML with vnu.jar

Since it's already installed in bin. Don't do this by default, since it
increases the time needed for tests by ~50%.

* fix: Stop the urlizer from urlizing in linkified mailto: text

* More HTML fixes

* More HTML validation fixes

* And more HTML fixes

* Fix floating badge

* Ignore unicode errors

* Only URLize docs that are existing

* Final fixes

* Don't URLize everything during test-crawl

* Feed HTML into vnu using python rather than Java to speed things up

* Allow test-crawl to start vnu on a different port

* Increase retry count to vnu. Restore batch size to 30.

* More HTML validation fixes

* Use urllib3 to make requests to vnu, since overriding requests_mock is tricky

* Undo commit of unmodified file

* Also urlize ftp links

* Fix matching of file name

* More HTML fixes

* Add `is_valid_url` filter

* weekday -> data-weekday

* urlencode URLs

* Add and use vnu_fmt_message. Bump vnu max buffer.

* Simplify doc_exists

* Don't add tab link to mail archive if the URL is invalid

* Run urlize_ietf_docs before linkify

Reduces the possibility of generating incorrect HTML

* Undo superfluous change

* Runner fixes

* Consolidate vnu message filtering into vnu_filter_message

* Correctly handle multiple persons with same name

* Minimze diff

* Fix HTML nits

* Print source snippet in vnu_fmt_message

* Only escape if there is something to escape

* Fix snippet

* Skip crufty old IPR declarations

* Only include modal when needed. Add handles.

* Fix wordwrap+linkification

* Update ietf/doc/templatetags/ietf_filters.py

* Update ietf/doc/templatetags/tests_ietf_filters.py

* Don't right-align second column

Author: larseggert

bin/test-crawl

@@ -23,6 +23,7 @@ RUN apt-get install -qy \
 	bash \
 	build-essential \
 	curl \
+    default-jdk \
     docker-ce-cli \
 	enscript \
 	gawk \

bin/vnu.jar

@@ -32,6 +32,7 @@ RUN apt-get install -qy \
 	bash \
 	build-essential \
 	curl \
+    default-jdk \
     docker-ce-cli \
 	enscript \
 	fish \

dev/tests/Dockerfile

@@ -4,6 +4,7 @@
 
 import datetime
 import re
+import os
 from urllib.parse import urljoin
 
 from email.utils import parseaddr
@@ -17,10 +18,13 @@
 from django.utils.encoding import force_text
 from django.utils.encoding import force_str # pyflakes:ignore force_str is used in the doctests
 from django.urls import reverse as urlreverse
+from django.core.cache import cache
+from django.core.validators import URLValidator
+from django.core.exceptions import ValidationError
 
 import debug                            # pyflakes:ignore
 
-from ietf.doc.models import BallotDocEvent
+from ietf.doc.models import BallotDocEvent, DocAlias
 from ietf.doc.models import ConsensusDocEvent
 from ietf.utils.html import sanitize_fragment
 from ietf.utils import log
@@ -184,49 +188,113 @@ def rfceditor_info_url(rfcnum : str):
     """Link to the RFC editor info page for an RFC"""
     return urljoin(settings.RFC_EDITOR_INFO_BASE_URL, f'rfc{rfcnum}')
 
+
+def doc_exists(name):
+    """Check whether a given document exists"""
+    def find_unique(n):
+        key = hash(n)
+        found = cache.get(key)
+        if not found:
+            exact = DocAlias.objects.filter(name=n).first()
+            found = exact.name if exact else "_"
+            cache.set(key, found)
+        return None if found == "_" else found
+
+    # all documents exist when tests are running
+    if settings.SERVER_MODE == 'test':
+        # unless we are running test-crawl, which would otherwise 404
+        if "DJANGO_URLIZE_IETF_DOCS_PRODUCTION" not in os.environ:
+            return True
+
+    # chop away extension
+    extension_split = re.search(r"^(.+)\.(txt|ps|pdf)$", name)
+    if extension_split:
+        name = extension_split.group(1)
+
+    if find_unique(name):
+        return True
+
+    # check for embedded rev - this may be ambiguous, so don't
+    # chop it off if we don't find a match
+    rev_split = re.search("^(.+)-([0-9]{2,})$", name)
+    if rev_split:
+        name = rev_split.group(1)
+        if find_unique(name):
+            return True
+
+    return False
+
+
+def link_charter_doc_match1(match):
+    if not doc_exists(match[0]):
+        return match[0]
+    return f'<a href="/doc/{match[1][:-1]}/{match[2]}/">{match[0]}</a>'
+
+
+def link_charter_doc_match2(match):
+    if not doc_exists(match[0]):
+        return match[0]
+    return f'<a href="/doc/{match[1][:-1]}/{match[2]}/">{match[0]}</a>'
+
+
 def link_non_charter_doc_match(match):
-    if len(match[3])==2 and match[3].isdigit():
+    if not doc_exists(match[0]):
+        return match[0]
+    if len(match[3]) == 2 and match[3].isdigit():
         return f'<a href="/doc/{match[2][:-1]}/{match[3]}/">{match[0]}</a>'
     else:
         return f'<a href="/doc/{match[2]}{match[3]}/">{match[0]}</a>'
 
-@register.filter(name='urlize_ietf_docs', is_safe=True, needs_autoescape=True)
+
+def link_other_doc_match(match):
+    # there may be whitespace in the match
+    doc = re.sub(r"\s+", "", match[0])
+    if not doc_exists(doc):
+        return match[0]
+    return f'<a href="/doc/{match[2].strip().lower()}{match[3]}/">{match[1]}</a>'
+
+
+@register.filter(name="urlize_ietf_docs", is_safe=True, needs_autoescape=True)
 def urlize_ietf_docs(string, autoescape=None):
     """
     Make occurrences of RFC NNNN and draft-foo-bar links to /doc/.
     """
     if autoescape and not isinstance(string, SafeData):
-        string = escape(string)
-    exp1 = r"\b(charter-(?:[\d\w\.+]+-)*)(\d\d-\d\d)(\.txt)?\b"
-    exp2 = r"\b(charter-(?:[\d\w\.+]+-)*)(\d\d)(\.txt)?\b"
+        if "<" in string:
+            string = escape(string)
+        else:
+            string = mark_safe(string)
+    exp1 = r"\b(?<![/\-:=#])(charter-(?:[\d\w\.+]+-)*)(\d\d-\d\d)(\.txt)?\b"
+    exp2 = r"\b(?<![/\-:=#])(charter-(?:[\d\w\.+]+-)*)(\d\d)(\.txt)?\b"
     if re.search(exp1, string):
         string = re.sub(
             exp1,
-            lambda x: f'<a href="/doc/{x[1][:-1]}/{x[2]}/">{x[0]}</a>',
+            link_charter_doc_match1,
             string,
             flags=re.IGNORECASE | re.ASCII,
         )
-    elif re.search(exp2, string): 
+    elif re.search(exp2, string):
         string = re.sub(
             exp2,
-            lambda x: f'<a href="/doc/{x[1][:-1]}/{x[2]}/">{x[0]}</a>',
+            link_charter_doc_match2,
             string,
             flags=re.IGNORECASE | re.ASCII,
         )
     string = re.sub(
-        r"\b(?<![/-])(((?:draft-|bofreq-|conflict-review-|status-change-)(?:[\d\w\.+]+-)*)([\d\w\.+]+?)(\.txt)?)\b",
+        r"\b(?<![/\-:=#])(((?:draft-|bofreq-|conflict-review-|status-change-)(?:[\d\w\.+]+-)*)([\d\w\.+]+?)(\.txt)?)\b(?![-@])",
         link_non_charter_doc_match,
         string,
         flags=re.IGNORECASE | re.ASCII,
     )
     string = re.sub(
         # r"\b((RFC|BCP|STD|FYI|(?:draft-|bofreq-|conflict-review-|status-change-|charter-)[-\d\w.+]+)\s*0*(\d+))\b",
-        r"\b(?<!-)((RFC|BCP|STD|FYI)\s*0*(\d+))\b",
-        lambda x: f'<a href="/doc/{x[2].strip().lower()}{x[3]}/">{x[1]}</a>',
+        r"\b(?<![/\-:=#])((RFC|BCP|STD|FYI)\s*0*(\d+))\b",
+        link_other_doc_match,
         string,
         flags=re.IGNORECASE | re.ASCII,
     )
     return mark_safe(string)
+
 urlize_ietf_docs = stringfilter(urlize_ietf_docs)
 
 @register.filter(name='urlize_related_source_list', is_safe=True, needs_autoescape=True)
@@ -444,7 +512,7 @@ def format_snippet(text, trunc_words=25):
 @register.simple_tag
 def doc_edit_button(url_name, *args, **kwargs):
     """Given URL name/args/kwargs, looks up the URL just like "url" tag and returns a properly formatted button for the document material tables."""
-    return mark_safe('<a class="btn btn-primary btn-sm" type="button" href="%s">Edit</a>' % (urlreverse(url_name, args=args, kwargs=kwargs)))
+    return mark_safe('<a class="btn btn-primary btn-sm" href="%s">Edit</a>' % (urlreverse(url_name, args=args, kwargs=kwargs)))
 
 @register.filter
 def textify(text):
@@ -765,3 +833,16 @@ def absurl(viewname, **kwargs):
     Uses settings.IDTRACKER_BASE_URL as the base.
     """
     return urljoin(settings.IDTRACKER_BASE_URL, urlreverse(viewname, kwargs=kwargs))
+
+
+@register.filter
+def is_valid_url(url):
+    """
+    Check if the given URL is syntactically valid
+    """
+    validate_url = URLValidator()
+    try:
+        validate_url(url)
+    except ValidationError:
+        return False
+    return True

docker/app.Dockerfile

@@ -46,14 +46,22 @@ def test_urlize_ietf_docs(self):
             ),
             (
                 "draft-madanapalli-nd-over-802.16-problems",
-                '<a href="/doc/draft-madanapalli-nd-over-802.16-problems/">draft-madanapalli-nd-over-802.16-problems</a>' 
+                '<a href="/doc/draft-madanapalli-nd-over-802.16-problems/">draft-madanapalli-nd-over-802.16-problems</a>'
             ),
             (
                  "draft-madanapalli-nd-over-802.16-problems-02.txt",
-                '<a href="/doc/draft-madanapalli-nd-over-802.16-problems/02/">draft-madanapalli-nd-over-802.16-problems-02.txt</a>'                
+                '<a href="/doc/draft-madanapalli-nd-over-802.16-problems/02/">draft-madanapalli-nd-over-802.16-problems-02.txt</a>'
+            ),
+            (
+                '<a href="mailto:draft-ietf-some-names@ietf.org">draft-ietf-some-names@ietf.org</a>',
+                '<a href="mailto:draft-ietf-some-names@ietf.org">draft-ietf-some-names@ietf.org</a>',
+            ),
+            (
+                "http://ieee802.org/1/files/public/docs2015/cn-thaler-Qcn-draft-PAR.pdf",
+                "http://ieee802.org/1/files/public/docs2015/cn-thaler-Qcn-draft-PAR.pdf"
             )
         ]
-        
+
         # Some edge cases scraped from existing old draft names
         for name in [
             # "draft-odell-8+8", # This fails since + matches the right side of \b

ietf/doc/templatetags/ietf_filters.py

@@ -23,6 +23,7 @@
 from ietf.review.utils import can_manage_review_requests_for_team
 from ietf.utils import log
 from ietf.utils.history import get_history_object_for, copy_many_to_many_for_history
+from ietf.doc.templatetags.ietf_filters import is_valid_url
 from functools import reduce
 
 def save_group_in_history(group):
@@ -208,7 +209,8 @@ def construct_group_menu_context(request, group, selected, group_type, others):
     entries.append(("Photos", urlreverse("ietf.group.views.group_photos", kwargs=kwargs)))
     entries.append(("Email expansions", urlreverse("ietf.group.views.email", kwargs=kwargs)))
     if group.list_archive.startswith("http:") or group.list_archive.startswith("https:") or group.list_archive.startswith("ftp:"):
-        entries.append((mark_safe("List archive »"), group.list_archive))
+        if is_valid_url(group.list_archive):
+            entries.append((mark_safe("List archive »"), group.list_archive))
 
 
     # actions

ietf/doc/templatetags/tests_ietf_filters.py

@@ -35,7 +35,7 @@
 
 # need to insert empty option for use in ChoiceField
 # countries.insert(0, ('', '-'*9 ))
-countries.insert(0, ('', ''))
+countries.insert(0, ('', '-' * 9))
 timezones.insert(0, ('', '-' * 9))
 
 # -------------------------------------------------
@@ -827,4 +827,4 @@ def sessiondetailsformset_factory(min_num=1, max_num=3):
         min_num=min_num,
         max_num=max_num,
         extra=max_num,  # only creates up to max_num total
-    )
+    )

ietf/group/utils.py

@@ -22,7 +22,9 @@
 
 class RecordingForm(forms.Form):
     external_url = forms.URLField(label='Url')
-    session = forms.ModelChoiceField(queryset=Session.objects,empty_label='')
+    session = forms.ModelChoiceField(queryset=Session.objects)
+    session.widget.attrs['class'] = "select2-field"
+    session.widget.attrs['data-minimum-input-length'] = 0
 
     def __init__(self, *args, **kwargs):
         self.meeting = kwargs.pop('meeting')