Refactor parsing function in code coverage plugin to split the actual parsing code from the lookup code.

1 files changed, 56 insertions, 49 deletions

diff --git a/Cython/Coverage.py b/Cython/Coverage.py
index 43b1bc9c5..87266461d 100644
--- a/Cython/Coverage.py
+++ b/Cython/Coverage.py
@@ -82,7 +82,7 @@ class Plugin(CoveragePlugin):
             #        is not from the main .pyx file but a file with a different
             #        name than the .c file (which prevents us from finding the
             #        .c file)
-            _, code = self._parse_lines(c_file, filename)
+            _, code = self._read_source_lines(c_file, filename)
             if code is None:
                 return None  # no source found
 
@@ -104,7 +104,7 @@ class Plugin(CoveragePlugin):
             c_file, _ = self._find_source_files(filename)
             if not c_file:
                 return None  # unknown file
-            rel_file_path, code = self._parse_lines(c_file, filename)
+            rel_file_path, code = self._read_source_lines(c_file, filename)
             if code is None:
                 return None  # no source found
         return CythonModuleReporter(c_file, filename, rel_file_path, code)
@@ -170,14 +170,14 @@ class Plugin(CoveragePlugin):
         for filename in os.listdir(dir_path):
             ext = splitext(filename)[1].lower()
             if ext in C_FILE_EXTENSIONS:
-                self._parse_lines(os.path.join(dir_path, filename), source_file)
+                self._read_source_lines(os.path.join(dir_path, filename), source_file)
                 if source_file in self._c_files_map:
                     return
         # not found? then try one package up
         if is_package_dir(dir_path):
             self._find_c_source_files(os.path.dirname(dir_path), source_file)
 
-    def _parse_lines(self, c_file, sourcefile):
+    def _read_source_lines(self, c_file, sourcefile):
         """
         Parse a Cython generated C/C++ source file and find the executable lines.
         Each executable line starts with a comment header that states source file
@@ -188,51 +188,7 @@ class Plugin(CoveragePlugin):
         if c_file in self._parsed_c_files:
             code_lines = self._parsed_c_files[c_file]
         else:
-            match_source_path_line = re.compile(r' */[*] +"(.*)":([0-9]+)$').match
-            match_current_code_line = re.compile(r' *[*] (.*) # <<<<<<+$').match
-            match_comment_end = re.compile(r' *[*]/$').match
-            match_trace_line = re.compile(r' *__Pyx_TraceLine\(([0-9]+),').match
-            not_executable = re.compile(
-                r'\s*c(?:type)?def\s+'
-                r'(?:(?:public|external)\s+)?'
-                r'(?:struct|union|enum|class)'
-                r'(\s+[^:]+|)\s*:'
-            ).match
-
-            code_lines = defaultdict(dict)
-            executable_lines = defaultdict(set)
-            current_filename = None
-            with open(c_file) as lines:
-                lines = iter(lines)
-                for line in lines:
-                    match = match_source_path_line(line)
-                    if not match:
-                        if '__Pyx_TraceLine(' in line and current_filename is not None:
-                            trace_line = match_trace_line(line)
-                            if trace_line:
-                                executable_lines[current_filename].add(int(trace_line.group(1)))
-                        continue
-                    filename, lineno = match.groups()
-                    current_filename = filename
-                    lineno = int(lineno)
-                    for comment_line in lines:
-                        match = match_current_code_line(comment_line)
-                        if match:
-                            code_line = match.group(1).rstrip()
-                            if not_executable(code_line):
-                                break
-                            code_lines[filename][lineno] = code_line
-                            break
-                        elif match_comment_end(comment_line):
-                            # unexpected comment format - false positive?
-                            break
-
-            # Remove lines that generated code but are not traceable.
-            for filename, lines in code_lines.items():
-                dead_lines = set(lines).difference(executable_lines.get(filename, ()))
-                for lineno in dead_lines:
-                    del lines[lineno]
-
+            code_lines = self._parse_cfile_lines(c_file)
             self._parsed_c_files[c_file] = code_lines
 
         if self._c_files_map is None:
@@ -246,6 +202,57 @@ class Plugin(CoveragePlugin):
             return (None,) * 2  # e.g. shared library file
         return self._c_files_map[sourcefile][1:]
 
+    def _parse_cfile_lines(self, c_file):
+        """
+        Parse a C file and extract all source file lines that generated executable code.
+        """
+        match_source_path_line = re.compile(r' */[*] +"(.*)":([0-9]+)$').match
+        match_current_code_line = re.compile(r' *[*] (.*) # <<<<<<+$').match
+        match_comment_end = re.compile(r' *[*]/$').match
+        match_trace_line = re.compile(r' *__Pyx_TraceLine\(([0-9]+),').match
+        not_executable = re.compile(
+            r'\s*c(?:type)?def\s+'
+            r'(?:(?:public|external)\s+)?'
+            r'(?:struct|union|enum|class)'
+            r'(\s+[^:]+|)\s*:'
+        ).match
+
+        code_lines = defaultdict(dict)
+        executable_lines = defaultdict(set)
+        current_filename = None
+
+        with open(c_file) as lines:
+            lines = iter(lines)
+            for line in lines:
+                match = match_source_path_line(line)
+                if not match:
+                    if '__Pyx_TraceLine(' in line and current_filename is not None:
+                        trace_line = match_trace_line(line)
+                        if trace_line:
+                            executable_lines[current_filename].add(int(trace_line.group(1)))
+                    continue
+                filename, lineno = match.groups()
+                current_filename = filename
+                lineno = int(lineno)
+                for comment_line in lines:
+                    match = match_current_code_line(comment_line)
+                    if match:
+                        code_line = match.group(1).rstrip()
+                        if not_executable(code_line):
+                            break
+                        code_lines[filename][lineno] = code_line
+                        break
+                    elif match_comment_end(comment_line):
+                        # unexpected comment format - false positive?
+                        break
+
+        # Remove lines that generated code but are not traceable.
+        for filename, lines in code_lines.items():
+            dead_lines = set(lines).difference(executable_lines.get(filename, ()))
+            for lineno in dead_lines:
+                del lines[lineno]
+        return code_lines
+
 
 class CythonModuleTracer(FileTracer):
     """