[PULL 12/17] qapi: Rewrite parsing of doc comment section symbols and tags

Markus Armbruster posted 17 patches 2 years, 9 months ago
Maintainers: Markus Armbruster <armbru@redhat.com>, Michael Roth <michael.roth@amd.com>, Peter Maydell <peter.maydell@linaro.org>, Paolo Bonzini <pbonzini@redhat.com>, "Marc-André Lureau" <marcandre.lureau@redhat.com>, "Daniel P. Berrangé" <berrange@redhat.com>, Thomas Huth <thuth@redhat.com>, "Philippe Mathieu-Daudé" <philmd@linaro.org>, "Michael S. Tsirkin" <mst@redhat.com>, Igor Mammedov <imammedo@redhat.com>, Ani Sinha <anisinha@redhat.com>, Eric Blake <eblake@redhat.com>, Gerd Hoffmann <kraxel@redhat.com>, Kevin Wolf <kwolf@redhat.com>, Hanna Reitz <hreitz@redhat.com>, "Gonglei (Arei)" <arei.gonglei@huawei.com>, Zhenwei Pi <pizhenwei@bytedance.com>, John Snow <jsnow@redhat.com>, Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>, Eduardo Habkost <eduardo@habkost.net>, Marcel Apfelbaum <marcel.apfelbaum@gmail.com>, Yanan Wang <wangyanan55@huawei.com>, Juan Quintela <quintela@redhat.com>, Peter Xu <peterx@redhat.com>, Leonardo Bras <leobras@redhat.com>, Jason Wang <jasowang@redhat.com>, Yuval Shaia <yuval.shaia.ml@gmail.com>, Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>, Jiri Pirko <jiri@resnulli.us>, Stefan Berger <stefanb@linux.vnet.ibm.com>, Stefan Hajnoczi <stefanha@redhat.com>, Lukas Straub <lukasstraub2@web.de>, Konstantin Kostiuk <kkostiuk@redhat.com>
There is a newer version of this series
[PULL 12/17] qapi: Rewrite parsing of doc comment section symbols and tags
Posted by Markus Armbruster 2 years, 9 months ago
To recognize a line starting with a section symbol and or tag, we
first split it at the first space, then examine the part left of the
space.  We can just as well examine the unsplit line, so do that.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20230428105429.1687850-13-armbru@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
---
 scripts/qapi/parser.py | 51 +++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 28 deletions(-)

diff --git a/scripts/qapi/parser.py b/scripts/qapi/parser.py
index ddc14ceaba..fc04c4573e 100644
--- a/scripts/qapi/parser.py
+++ b/scripts/qapi/parser.py
@@ -560,12 +560,12 @@ def end_comment(self) -> None:
         self._switch_section(QAPIDoc.NullSection(self._parser))
 
     @staticmethod
-    def _is_section_tag(name: str) -> bool:
-        return name in ('Returns:', 'Since:',
-                        # those are often singular or plural
-                        'Note:', 'Notes:',
-                        'Example:', 'Examples:',
-                        'TODO:')
+    def _match_at_name_colon(string: str) -> re.Match:
+        return re.match(r'@([^:]*): *', string)
+
+    @staticmethod
+    def _match_section_tag(string: str) -> re.Match:
+        return re.match(r'(Returns|Since|Notes?|Examples?|TODO): *', string)
 
     def _append_body_line(self, line: str) -> None:
         """
@@ -581,7 +581,6 @@ def _append_body_line(self, line: str) -> None:
 
         Else, append the line to the current section.
         """
-        name = line.split(' ', 1)[0]
         # FIXME not nice: things like '#  @foo:' and '# @foo: ' aren't
         # recognized, and get silently treated as ordinary text
         if not self.symbol and not self.body.text and line.startswith('@'):
@@ -595,12 +594,12 @@ def _append_body_line(self, line: str) -> None:
                     self._parser, "name required after '@'")
         elif self.symbol:
             # This is a definition documentation block
-            if name.startswith('@') and name.endswith(':'):
+            if self._match_at_name_colon(line):
                 self._append_line = self._append_args_line
                 self._append_args_line(line)
             elif line == 'Features:':
                 self._append_line = self._append_features_line
-            elif self._is_section_tag(name):
+            elif self._match_section_tag(line):
                 self._append_line = self._append_various_line
                 self._append_various_line(line)
             else:
@@ -621,16 +620,15 @@ def _append_args_line(self, line: str) -> None:
         Else, append the line to the current section.
 
         """
-        name = line.split(' ', 1)[0]
-
-        if name.startswith('@') and name.endswith(':'):
+        if match := self._match_at_name_colon(line):
             # If line is "@arg:   first line of description", find
             # the index of 'f', which is the indent we expect for any
             # following lines.  We then remove the leading "@arg:"
             # from line and replace it with spaces so that 'f' has the
             # same index as it did in the original line and can be
             # handled the same way we will handle following lines.
-            indent = must_match(r'@\S*:\s*', line).end()
+            name = match.group(1)
+            indent = match.end()
             line = line[indent:]
             if not line:
                 # Line was just the "@arg:" header
@@ -638,8 +636,8 @@ def _append_args_line(self, line: str) -> None:
                 indent = -1
             else:
                 line = ' ' * indent + line
-            self._start_args_section(name[1:-1], indent)
-        elif self._is_section_tag(name):
+            self._start_args_section(name, indent)
+        elif self._match_section_tag(line):
             self._append_line = self._append_various_line
             self._append_various_line(line)
             return
@@ -656,16 +654,15 @@ def _append_args_line(self, line: str) -> None:
         self._append_freeform(line)
 
     def _append_features_line(self, line: str) -> None:
-        name = line.split(' ', 1)[0]
-
-        if name.startswith('@') and name.endswith(':'):
+        if match := self._match_at_name_colon(line):
             # If line is "@arg:   first line of description", find
             # the index of 'f', which is the indent we expect for any
             # following lines.  We then remove the leading "@arg:"
             # from line and replace it with spaces so that 'f' has the
             # same index as it did in the original line and can be
             # handled the same way we will handle following lines.
-            indent = must_match(r'@\S*:\s*', line).end()
+            name = match.group(1)
+            indent = match.end()
             line = line[indent:]
             if not line:
                 # Line was just the "@arg:" header
@@ -673,8 +670,8 @@ def _append_features_line(self, line: str) -> None:
                 indent = -1
             else:
                 line = ' ' * indent + line
-            self._start_features_section(name[1:-1], indent)
-        elif self._is_section_tag(name):
+            self._start_features_section(name, indent)
+        elif self._match_section_tag(line):
             self._append_line = self._append_various_line
             self._append_various_line(line)
             return
@@ -698,13 +695,11 @@ def _append_various_line(self, line: str) -> None:
 
         Else, append the line to the current section.
         """
-        name = line.split(' ', 1)[0]
-
-        if name.startswith('@') and name.endswith(':'):
+        if match := self._match_at_name_colon(line):
             raise QAPIParseError(self._parser,
-                                 "'%s' can't follow '%s' section"
-                                 % (name, self.sections[0].name))
-        if self._is_section_tag(name):
+                                 "'@%s:' can't follow '%s' section"
+                                 % (match.group(1), self.sections[0].name))
+        if match := self._match_section_tag(line):
             # If line is "Section:   first line of description", find
             # the index of 'f', which is the indent we expect for any
             # following lines.  We then remove the leading "Section:"
@@ -719,7 +714,7 @@ def _append_various_line(self, line: str) -> None:
                 indent = 0
             else:
                 line = ' ' * indent + line
-            self._start_section(name[:-1], indent)
+            self._start_section(match.group(1), indent)
 
         self._append_freeform(line)
 
-- 
2.39.2