bpo-44010: IDLE: colorize pattern-matching soft keywords

Doc/library/idle.rst

@@ -613,6 +613,12 @@ keywords, builtin class and function names, names following ``class`` and
 ``def``, strings, and comments. For any text window, these are the cursor (when
 present), found text (when possible), and selected text.
 
+IDLE also highlights the :ref:`soft keywords <soft-keywords>` :keyword:`match`,
+:keyword:`case <match>`, and :keyword:`_ <wildcard-patterns>` in
+pattern-matching statements. However, this highlighting is not perfect and
+will be incorrect in some rare cases, including some ``_``-s in ``case``
+patterns.
+
 Text coloring is done in the background, so uncolorized text is occasionally
 visible.  To change the color scheme, use the Configure IDLE dialog
 Highlighting tab.  The marking of debugger breakpoint lines in the editor and

Doc/whatsnew/3.10.rst

@@ -1030,6 +1030,12 @@ Terry Jan Reedy in :issue:`37892`.)
 We expect to backport these shell changes to a future 3.9 maintenance
 release.
 
+Highlight the new :ref:`soft keywords <soft-keywords>` :keyword:`match`,
+:keyword:`case <match>`, and :keyword:`_ <wildcard-patterns>` in
+pattern-matching statements. However, this highlighting is not perfect
+and will be incorrect in some rare cases, including some ``_``-s in
+``case`` patterns.  (Contributed by Tal Einat in bpo-44010.)
+
 importlib.metadata
 ------------------
 

Lib/idlelib/colorizer.py

@@ -16,6 +16,32 @@ def any(name, alternates):
 
 def make_pat():
     kw = r"\b" + any("KEYWORD", keyword.kwlist) + r"\b"
+    match_softkw = (
+        r"^[ \t]*" +  # at beginning of line + possible indentation
+        r"(?P<MATCH_SOFTKW>match)\b" +
+        r"(?![ \t]*(?:" + "|".join([  # not followed by ...
+            r"[:,;=^&|@~)\]}]",  # a character which means it can't be a
+                                 # pattern-matching statement
+            r"\b(?:" + r"|".join(keyword.kwlist) + r")\b",  # a keyword
+        ]) +
+        r"))"
+    )
+    case_default = (
+        r"^[ \t]*" +  # at beginning of line + possible indentation
+        r"(?P<CASE_SOFTKW>case)" +
+        r"[ \t]+(?P<CASE_DEFAULT_UNDERSCORE>_\b)"
+    )
+    case_softkw_and_pattern = (
+        r"^[ \t]*" +  # at beginning of line + possible indentation
+        r"(?P<CASE_SOFTKW2>case)\b" +
+        r"(?![ \t]*(?:" + "|".join([  # not followed by ...
+            r"_\b",  # a lone underscore
+            r"[:,;=^&|@~)\]}]",  # a character which means it can't be a
+                                 # pattern-matching case
+            r"\b(?:" + r"|".join(keyword.kwlist) + r")\b",  # a keyword
+        ]) +
+        r"))"
+    )
     builtinlist = [str(name) for name in dir(builtins)
                    if not name.startswith('_') and
                    name not in keyword.kwlist]
@@ -27,12 +53,29 @@ def make_pat():
     sq3string = stringprefix + r"'''[^'\\]*((\\.|'(?!''))[^'\\]*)*(''')?"
     dq3string = stringprefix + r'"""[^"\\]*((\\.|"(?!""))[^"\\]*)*(""")?'
     string = any("STRING", [sq3string, dq3string, sqstring, dqstring])
-    return (kw + "|" + builtin + "|" + comment + "|" + string +
-            "|" + any("SYNC", [r"\n"]))
+    prog = re.compile("|".join([
+                                builtin, comment, string, kw,
+                                match_softkw, case_default,
+                                case_softkw_and_pattern,
+                                any("SYNC", [r"\n"]),
+                               ]),
+                      re.DOTALL | re.MULTILINE)
+    return prog
 
 
-prog = re.compile(make_pat(), re.S)
-idprog = re.compile(r"\s+(\w+)", re.S)
+prog = make_pat()
+idprog = re.compile(r"\s+(\w+)")
+prog_group_name_to_tag = {
+    "MATCH_SOFTKW": "KEYWORD",
+    "CASE_SOFTKW": "KEYWORD",
+    "CASE_DEFAULT_UNDERSCORE": "KEYWORD",
+    "CASE_SOFTKW2": "KEYWORD",
+}
+
+
+def matched_named_groups(re_match):
+    "Get only the non-empty named groups from an re.Match object."
+    return ((k, v) for (k, v) in re_match.groupdict().items() if v)
 
 
 def color_config(text):
@@ -231,14 +274,10 @@ def recolorize(self):
     def recolorize_main(self):
         "Evaluate text and apply colorizing tags."
         next = "1.0"
-        while True:
-            item = self.tag_nextrange("TODO", next)
-            if not item:
-                break
-            head, tail = item
-            self.tag_remove("SYNC", head, tail)
-            item = self.tag_prevrange("SYNC", head)
-            head = item[1] if item else "1.0"
+        while todo_tag_range := self.tag_nextrange("TODO", next):
+            self.tag_remove("SYNC", todo_tag_range[0], todo_tag_range[1])
+            sync_tag_range = self.tag_prevrange("SYNC", todo_tag_range[0])
+            head = sync_tag_range[1] if sync_tag_range else "1.0"
 
             chars = ""
             next = head
@@ -256,23 +295,8 @@ def recolorize_main(self):
                     return
                 for tag in self.tagdefs:
                     self.tag_remove(tag, mark, next)
-                chars = chars + line
-                m = self.prog.search(chars)
-                while m:
-                    for key, value in m.groupdict().items():
-                        if value:
-                            a, b = m.span(key)
-                            self.tag_add(key,
-                                         head + "+%dc" % a,
-                                         head + "+%dc" % b)
-                            if value in ("def", "class"):
-                                m1 = self.idprog.match(chars, b)
-                                if m1:
-                                    a, b = m1.span(1)
-                                    self.tag_add("DEFINITION",
-                                                 head + "+%dc" % a,
-                                                 head + "+%dc" % b)
-                    m = self.prog.search(chars, m.end())
+                chars += line
+                self._add_tags_in_section(chars, head)
                 if "SYNC" in self.tag_names(next + "-1c"):
                     head = next
                     chars = ""
@@ -291,6 +315,40 @@ def recolorize_main(self):
                     if DEBUG: print("colorizing stopped")
                     return
 
+    def _add_tag(self, start, end, head, matched_group_name):
+        """Add a tag to a given range in the text widget.
+
+        This is a utility function, receiving the range as `start` and
+        `end` positions, each of which is a number of characters
+        relative to the given `head` index in the text widget.
+
+        The tag to add is determined by `matched_group_name`, which is
+        the name of a regular expression "named group" as matched by
+        by the relevant highlighting regexps.
+        """
+        tag = prog_group_name_to_tag.get(matched_group_name,
+                                         matched_group_name)
+        self.tag_add(tag,
+                     f"{head}+{start:d}c",
+                     f"{head}+{end:d}c")
+
+    def _add_tags_in_section(self, chars, head):
+        """Parse and add highlighting tags to a given part of the text.
+
+        `chars` is a string with the text to parse and to which
+        highlighting is to be applied.
+
+            `head` is the index in the text widget where the text is found.
+        """
+        for m in self.prog.finditer(chars):
+            for name, matched_text in matched_named_groups(m):
+                a, b = m.span(name)
+                self._add_tag(a, b, head, name)
+                if matched_text in ("def", "class"):
+                    if m1 := self.idprog.match(chars, b):
+                        a, b = m1.span(1)
+                        self._add_tag(a, b, head, "DEFINITION")
+
     def removecolors(self):
         "Remove all colorizing tags."
         for tag in self.tagdefs:
@@ -299,27 +357,14 @@ def removecolors(self):
 
 def _color_delegator(parent):  # htest #
     from tkinter import Toplevel, Text
+    from idlelib.idle_test.test_colorizer import source
     from idlelib.percolator import Percolator
 
     top = Toplevel(parent)
     top.title("Test ColorDelegator")
     x, y = map(int, parent.geometry().split('+')[1:])
-    top.geometry("700x250+%d+%d" % (x + 20, y + 175))
-    source = (
-        "if True: int ('1') # keyword, builtin, string, comment\n"
-        "elif False: print(0)\n"
-        "else: float(None)\n"
-        "if iF + If + IF: 'keyword matching must respect case'\n"
-        "if'': x or''  # valid keyword-string no-space combinations\n"
-        "async def f(): await g()\n"
-        "# All valid prefixes for unicode and byte strings should be colored.\n"
-        "'x', '''x''', \"x\", \"\"\"x\"\"\"\n"
-        "r'x', u'x', R'x', U'x', f'x', F'x'\n"
-        "fr'x', Fr'x', fR'x', FR'x', rf'x', rF'x', Rf'x', RF'x'\n"
-        "b'x',B'x', br'x',Br'x',bR'x',BR'x', rb'x', rB'x',Rb'x',RB'x'\n"
-        "# Invalid combinations of legal characters should be half colored.\n"
-        "ur'x', ru'x', uf'x', fu'x', UR'x', ufr'x', rfu'x', xf'x', fx'x'\n"
-        )
+    top.geometry("700x550+%d+%d" % (x + 20, y + 175))
+
     text = Text(top, background="white")
     text.pack(expand=1, fill="both")
     text.insert("insert", source)

Lib/idlelib/help.html

@@ -5,7 +5,7 @@
   <head>
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-    <title>IDLE &#8212; Python 3.10.0a6 documentation</title>
+    <title>IDLE &#8212; Python 3.11.0a0 documentation</title>
     <link rel="stylesheet" href="../_static/pydoctheme.css" type="text/css" />
     <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
 
@@ -18,7 +18,7 @@
     <script src="../_static/sidebar.js"></script>
 
     <link rel="search" type="application/opensearchdescription+xml"
-          title="Search within Python 3.10.0a6 documentation"
+          title="Search within Python 3.11.0a0 documentation"
           href="../_static/opensearch.xml"/>
     <link rel="author" title="About these documents" href="../about.html" />
     <link rel="index" title="Index" href="../genindex.html" />
@@ -71,7 +71,7 @@ <h3>Navigation</h3>
 
 
     <li id="cpython-language-and-version">
-      <a href="../index.html">3.10.0a6 Documentation</a> &#187;
+      <a href="../index.html">3.11.0a0 Documentation</a> &#187;
     </li>
 
           <li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> &#187;</li>
@@ -102,7 +102,7 @@ <h3>Navigation</h3>
 
   <div class="section" id="idle">
 <span id="id1"></span><h1>IDLE<a class="headerlink" href="#idle" title="Permalink to this headline">¶</a></h1>
-<p><strong>Source code:</strong> <a class="reference external" href="https://github.com/python/cpython/tree/master/Lib/idlelib/">Lib/idlelib/</a></p>
+<p><strong>Source code:</strong> <a class="reference external" href="https://github.com/python/cpython/tree/main/Lib/idlelib/">Lib/idlelib/</a></p>
 <hr class="docutils" id="index-0" />
 <p>IDLE is Python’s Integrated Development and Learning Environment.</p>
 <p>IDLE has the following features:</p>
@@ -581,6 +581,11 @@ <h3>Text colors<a class="headerlink" href="#text-colors" title="Permalink to thi
 keywords, builtin class and function names, names following <code class="docutils literal notranslate"><span class="pre">class</span></code> and
 <code class="docutils literal notranslate"><span class="pre">def</span></code>, strings, and comments. For any text window, these are the cursor (when
 present), found text (when possible), and selected text.</p>
+<p>IDLE also highlights the <a class="reference internal" href="../reference/lexical_analysis.html#soft-keywords"><span class="std std-ref">soft keywords</span></a> <a class="reference internal" href="../reference/compound_stmts.html#match"><code class="xref std std-keyword docutils literal notranslate"><span class="pre">match</span></code></a>,
+<a class="reference internal" href="../reference/compound_stmts.html#match"><code class="xref std std-keyword docutils literal notranslate"><span class="pre">case</span></code></a>, and <a class="reference internal" href="../reference/compound_stmts.html#wildcard-patterns"><code class="xref std std-keyword docutils literal notranslate"><span class="pre">_</span></code></a> in
+pattern-matching statements. However, this highlighting is not perfect and
+will be incorrect in some rare cases, including some <code class="docutils literal notranslate"><span class="pre">_</span></code>-s in <code class="docutils literal notranslate"><span class="pre">case</span></code>
+patterns.</p>
 <p>Text coloring is done in the background, so uncolorized text is occasionally
 visible.  To change the color scheme, use the Configure IDLE dialog
 Highlighting tab.  The marking of debugger breakpoint lines in the editor and
@@ -685,7 +690,7 @@ <h3>Running user code<a class="headerlink" href="#running-user-code" title="Perm
 directly with Python in a text-mode system console or terminal window.
 However, the different interface and operation occasionally affect
 visible results.  For instance, <code class="docutils literal notranslate"><span class="pre">sys.modules</span></code> starts with more entries,
-and <code class="docutils literal notranslate"><span class="pre">threading.activeCount()</span></code> returns 2 instead of 1.</p>
+and <code class="docutils literal notranslate"><span class="pre">threading.active_count()</span></code> returns 2 instead of 1.</p>
 <p>By default, IDLE runs user code in a separate OS process rather than in
 the user interface process that runs the shell and editor.  In the execution
 process, it replaces <code class="docutils literal notranslate"><span class="pre">sys.stdin</span></code>, <code class="docutils literal notranslate"><span class="pre">sys.stdout</span></code>, and <code class="docutils literal notranslate"><span class="pre">sys.stderr</span></code>
@@ -939,7 +944,7 @@ <h3>This Page</h3>
     <ul class="this-page-menu">
       <li><a href="../bugs.html">Report a Bug</a></li>
       <li>
-        <a href="https://github.com/python/cpython/blob/master/Doc/library/idle.rst"
+        <a href="https://github.com/python/cpython/blob/main/Doc/library/idle.rst"
             rel="nofollow">Show Source
         </a>
       </li>
@@ -971,7 +976,7 @@ <h3>Navigation</h3>
 
 
     <li id="cpython-language-and-version">
-      <a href="../index.html">3.10.0a6 Documentation</a> &#187;
+      <a href="../index.html">3.11.0a0 Documentation</a> &#187;
     </li>
 
           <li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> &#187;</li>
@@ -997,13 +1002,19 @@ <h3>Navigation</h3>
     <div class="footer">
     &copy; <a href="../copyright.html">Copyright</a> 2001-2021, Python Software Foundation.
     <br />
+    This page is licensed under the Python Software Foundation License Version 2.
+    <br />
+    Examples, recipes, and other code in the documentation are additionally licensed under the Zero Clause BSD License.
+    <br />
+    See <a href="">History and License</a> for more information.
+    <br /><br />
 
     The Python Software Foundation is a non-profit corporation.
 <a href="https://www.python.org/psf/donations/">Please donate.</a>
 <br />
     <br />
 
-    Last updated on Mar 29, 2021.
+    Last updated on May 11, 2021.
     <a href="https://docs.python.org/3/bugs.html">Found a bug</a>?
     <br />