bpo-18387: Add 'symbols' link to pydoc's html menu bar

Author: CuriousLearner

Lib/pydoc.py

@@ -75,6 +75,7 @@ class or function within a module or module in a package.  If the
 import warnings
 from annotationlib import Format
 from collections import deque
+from html import escape as html_escape
 from reprlib import Repr
 from traceback import format_exception_only
 
@@ -597,9 +598,6 @@ def __init__(self):
         self.maxdict = 10
         self.maxstring = self.maxother = 100
 
-    def escape(self, text):
-        return replace(text, '&', '&amp;', '<', '&lt;', '>', '&gt;')
-
     def repr(self, object):
         return Repr.repr(self, object)
 
@@ -608,26 +606,26 @@ def repr1(self, x, level):
             methodname = 'repr_' + '_'.join(type(x).__name__.split())
             if hasattr(self, methodname):
                 return getattr(self, methodname)(x, level)
-        return self.escape(cram(stripid(repr(x)), self.maxother))
+        return html_escape(cram(stripid(repr(x)), self.maxother))
 
     def repr_string(self, x, level):
         test = cram(x, self.maxstring)
         testrepr = repr(test)
         if '\\' in test and '\\' not in replace(testrepr, r'\\', ''):
             # Backslashes are only literal in the string and are never
             # needed to make any special characters, so show a raw string.
-            return 'r' + testrepr[0] + self.escape(test) + testrepr[0]
+            return 'r' + testrepr[0] + html_escape(test) + testrepr[0]
         return re.sub(r'((\\[\\abfnrtv\'"]|\\[0-9]..|\\x..|\\u....)+)',
                       r'<span class="repr">\1</span>',
-                      self.escape(testrepr))
+                      html_escape(testrepr, quote=False))
 
     repr_str = repr_string
 
     def repr_instance(self, x, level):
         try:
-            return self.escape(cram(stripid(repr(x)), self.maxstring))
+            return html_escape(cram(stripid(repr(x)), self.maxstring))
         except:
-            return self.escape('<%s instance>' % x.__class__.__name__)
+            return html_escape('<%s instance>' % x.__class__.__name__)
 
     repr_unicode = repr_string
 
@@ -638,7 +636,6 @@ class HTMLDoc(Doc):
 
     _repr_instance = HTMLRepr()
     repr = _repr_instance.repr
-    escape = _repr_instance.escape
 
     def page(self, title, contents):
         """Format an HTML page."""
@@ -689,7 +686,7 @@ def bigsection(self, title, *args):
 
     def preformat(self, text):
         """Format literal preformatted text."""
-        text = self.escape(text.expandtabs())
+        text = html_escape(text.expandtabs(), quote=False)
         return replace(text, '\n\n', '\n \n', '\n\n', '\n \n',
                              ' ', '&nbsp;', '\n', '<br>\n')
 
@@ -767,7 +764,7 @@ def filelink(self, url, path):
     def markup(self, text, escape=None, funcs={}, classes={}, methods={}):
         """Mark up some plain text, given a context of symbols to look for.
         Each context dictionary maps object names to anchor names."""
-        escape = escape or self.escape
+        escape = escape or html_escape
         results = []
         here = 0
         pattern = re.compile(r'\b((http|https|ftp)://\S+[\w/]|'
@@ -850,9 +847,9 @@ def docmodule(self, object, name=None, mod=None, *ignored):
             version = str(object.__version__)
             if version[:11] == '$' + 'Revision: ' and version[-1:] == '$':
                 version = version[11:-1].strip()
-            info.append('version %s' % self.escape(version))
+            info.append('version %s' % html_escape(version))
         if hasattr(object, '__date__'):
-            info.append(self.escape(str(object.__date__)))
+            info.append(html_escape(str(object.__date__)))
         if info:
             head = head + ' (%s)' % ', '.join(info)
         docloc = self.getdocloc(object)
@@ -2212,6 +2209,11 @@ def showsymbol(self, symbol):
         topic, _, xrefs = target.partition(' ')
         self.showtopic(topic, xrefs)
 
+    def _getsymbol(self, symbol):
+        target = self.symbols[symbol]
+        topic, _, xrefs = target.partition(' ')
+        return self._gettopic(topic, xrefs)
+
     def listmodules(self, key=''):
         if key:
             self.output.write('''
@@ -2377,6 +2379,7 @@ def _start_server(urlhandler, hostname, port):
     import email.message
     import select
     import threading
+    from urllib.parse import unquote
 
     class DocHandler(http.server.BaseHTTPRequestHandler):
 
@@ -2496,11 +2499,14 @@ def page(self, title, contents):
 %s</head><body>%s<div style="clear:both;padding-top:.5em;">%s</div>
 </body></html>''' % (title, css_link, html_navbar(), contents)
 
+        def filelink(self, url, path):
+            return ('<a href="getfile?key=%s">%s</a>' %
+                (html_escape(url), html_escape(path)))
 
     html = _HTMLDoc()
 
     def html_navbar():
-        version = html.escape("%s [%s, %s]" % (platform.python_version(),
+        version = html_escape("%s [%s, %s]" % (platform.python_version(),
                                                platform.python_build()[0],
                                                platform.python_compiler()))
         return """
@@ -2512,6 +2518,7 @@ def html_navbar():
                   <a href="index.html">Module Index</a>
                   : <a href="topics.html">Topics</a>
                   : <a href="keywords.html">Keywords</a>
+                  : <a href="symbols.html">Symbols</a>
                 </div>
                 <div>
                     <form action="get" style='display:inline;'>
@@ -2524,7 +2531,7 @@ def html_navbar():
                     </form>
                 </div>
             </div>
-            """ % (version, html.escape(platform.platform(terse=True)))
+            """ % (version, html_escape(platform.platform(terse=True)))
 
     def html_index():
         """Module Index page."""
@@ -2580,7 +2587,20 @@ def bltinlink(name):
             'key = %s' % key, 'index', '<br>'.join(results))
         return 'Search Results', contents
 
-    def html_topics():
+    def html_getfile(path):
+        """Get and display a source file listing safely."""
+        path = urllib.parse.unquote(path)
+        with tokenize.open(path) as fp:
+            lines = html_escape(fp.read())
+        body = '<pre>%s</pre>' % lines
+        heading = html.heading(
+            '<strong class="title">File Listing</strong>',
+        )
+        contents = heading + html.bigsection(
+            'File: %s' % path, 'index', body)
+        return 'getfile %s' % path, contents
+
+    def html_topicindex(title):
         """Index of topic texts available."""
 
         def bltinlink(name):
@@ -2589,37 +2609,34 @@ def bltinlink(name):
         heading = html.heading(
             '<strong class="title">INDEX</strong>',
         )
-        names = sorted(Helper.topics.keys())
-
-        contents = html.multicolumn(names, bltinlink)
-        contents = heading + html.bigsection(
-            'Topics', 'index', contents)
-        return 'Topics', contents
-
-    def html_keywords():
-        """Index of keywords."""
-        heading = html.heading(
-            '<strong class="title">INDEX</strong>',
-        )
-        names = sorted(Helper.keywords.keys())
 
-        def bltinlink(name):
-            return '<a href="topic?key=%s">%s</a>' % (name, name)
+        keys = {
+            'topics': Helper.topics.keys,
+            'keywords': Helper.keywords.keys,
+            'symbols': Helper.symbols.keys,
+        }
+        names = sorted(keys[title]())
 
         contents = html.multicolumn(names, bltinlink)
         contents = heading + html.bigsection(
-            'Keywords', 'index', contents)
-        return 'Keywords', contents
+            title.capitalize(), 'index', contents)
+        return title.capitalize(), contents
 
     def html_topicpage(topic):
         """Topic or keyword help page."""
         buf = io.StringIO()
         htmlhelp = Helper(buf, buf)
-        contents, xrefs = htmlhelp._gettopic(topic)
         if topic in htmlhelp.keywords:
             title = 'KEYWORD'
-        else:
+            contents, xrefs = htmlhelp._gettopic(topic)
+        elif topic in htmlhelp.topics:
             title = 'TOPIC'
+            contents, xrefs = htmlhelp._gettopic(topic)
+        elif topic in htmlhelp.symbols:
+            title = 'SYMBOL'
+            contents, xrefs = htmlhelp._getsymbol(topic)
+        else:
+            raise ValueError('could not find topic %s' % repr(topic))
         heading = html.heading(
             '<strong class="title">%s</strong>' % title,
         )
@@ -2629,7 +2646,7 @@ def html_topicpage(topic):
             xrefs = sorted(xrefs.split())
 
             def bltinlink(name):
-                return '<a href="topic?key=%s">%s</a>' % (name, name)
+                return '<a href="topic?key=%s">%s</a>' % (html_escape(name), html_escape(name))
 
             xrefs = html.multicolumn(xrefs, bltinlink)
             xrefs = html.section('Related help topics: ', 'index', xrefs)
@@ -2648,7 +2665,7 @@ def html_error(url, exc):
         heading = html.heading(
             '<strong class="title">Error</strong>',
         )
-        contents = '<br>'.join(html.escape(line) for line in
+        contents = '<br>'.join(html_escape(line) for line in
                                format_exception_only(type(exc), exc))
         contents = heading + html.bigsection(url, 'error', contents)
         return "Error - %s" % url, contents
@@ -2661,21 +2678,21 @@ def get_html_page(url):
         try:
             if url in ("", "index"):
                 title, content = html_index()
-            elif url == "topics":
-                title, content = html_topics()
-            elif url == "keywords":
-                title, content = html_keywords()
-            elif '=' in url:
-                op, _, url = url.partition('=')
-                if op == "search?key":
+            elif url in ("topics", "keywords", "symbols"):
+                title, content = html_topicindex(url)
+            elif '?key=' in url:
+                op, _, url = url.partition('?key=')
+                if op == "search":
                     title, content = html_search(url)
-                elif op == "topic?key":
+                elif op == "getfile":
+                    title, content = html_getfile(url)
+                elif op == "topic":
                     # try topics first, then objects.
                     try:
                         title, content = html_topicpage(url)
                     except ValueError:
                         title, content = html_getobj(url)
-                elif op == "get?key":
+                elif op == "get":
                     # try objects first, then topics.
                     if url in ("", "index"):
                         title, content = html_index()
@@ -2870,5 +2887,6 @@ class BadUsage(Exception): pass
     it names a directory, documentation is written for all the contents.
 """.format(cmd=cmd, sep=os.sep))
 
+
 if __name__ == '__main__':
     cli()

Lib/test/test_pydoc/test_pydoc.py

@@ -2102,6 +2102,7 @@ def test_url_requests(self):
             ("index", "Pydoc: Index of Modules"),
             ("topics", "Pydoc: Topics"),
             ("keywords", "Pydoc: Keywords"),
+            ("symbols", "Pydoc: Symbols"),
             ("pydoc", "Pydoc: module pydoc"),
             ("get?key=pydoc", "Pydoc: module pydoc"),
             ("search?key=pydoc", "Pydoc: Search Results"),

Misc/NEWS.d/next/Library/2019-05-10-02-37-20.bpo-18387.ppwPIb.rst

@@ -0,0 +1,2 @@
+Add 'symbols' link to pydoc's html menu bar. Original patch by Ron Adam.
+Enhanced by Sanyam Khurana.