]> git.madduck.net Git - etc/vim.git/blobdiff - blib2to3/pgen2/driver.py

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

add change log entry (#764)
[etc/vim.git] / blib2to3 / pgen2 / driver.py
index 5cdd2e59e6156cecd8ffa3cebc822b4be20ef7ae..63b60bbad56f533924752f2dd86aea148ffd4f5a 100644 (file)
@@ -32,7 +32,7 @@ class Driver(object):
     def __init__(self, grammar, convert=None, logger=None):
         self.grammar = grammar
         if logger is None:
     def __init__(self, grammar, convert=None, logger=None):
         self.grammar = grammar
         if logger is None:
-            logger = logging.getLogger()
+            logger = logging.getLogger(__name__)
         self.logger = logger
         self.convert = convert
 
         self.logger = logger
         self.convert = convert
 
@@ -43,6 +43,7 @@ class Driver(object):
         p.setup()
         lineno = 1
         column = 0
         p.setup()
         lineno = 1
         column = 0
+        indent_columns = []
         type = value = start = end = line_text = None
         prefix = ""
         for quintuple in tokens:
         type = value = start = end = line_text = None
         prefix = ""
         for quintuple in tokens:
@@ -69,20 +70,19 @@ class Driver(object):
             if debug:
                 self.logger.debug("%s %r (prefix=%r)",
                                   token.tok_name[type], value, prefix)
             if debug:
                 self.logger.debug("%s %r (prefix=%r)",
                                   token.tok_name[type], value, prefix)
-            if type in {token.INDENT, token.DEDENT}:
-                _prefix = prefix
+            if type == token.INDENT:
+                indent_columns.append(len(value))
+                _prefix = prefix + value
                 prefix = ""
                 prefix = ""
+                value = ""
+            elif type == token.DEDENT:
+                _indent_col = indent_columns.pop()
+                prefix, _prefix = self._partially_consume_prefix(prefix, _indent_col)
             if p.addtoken(type, value, (prefix, start)):
                 if debug:
                     self.logger.debug("Stop.")
                 break
             prefix = ""
             if p.addtoken(type, value, (prefix, start)):
                 if debug:
                     self.logger.debug("Stop.")
                 break
             prefix = ""
-            if type == token.INDENT:
-                if _prefix.startswith(value):
-                    # Don't double-indent.  Since we're delaying the prefix that
-                    # would normally belong to INDENT, we need to put the value
-                    # at the end versus at the beginning.
-                    _prefix = _prefix[len(value):] + value
             if type in {token.INDENT, token.DEDENT}:
                 prefix = _prefix
             lineno, column = end
             if type in {token.INDENT, token.DEDENT}:
                 prefix = _prefix
             lineno, column = end
@@ -114,19 +114,50 @@ class Driver(object):
         tokens = tokenize.generate_tokens(io.StringIO(text).readline)
         return self.parse_tokens(tokens, debug)
 
         tokens = tokenize.generate_tokens(io.StringIO(text).readline)
         return self.parse_tokens(tokens, debug)
 
-
-def _generate_pickle_name(gt):
+    def _partially_consume_prefix(self, prefix, column):
+        lines = []
+        current_line = ""
+        current_column = 0
+        wait_for_nl = False
+        for char in prefix:
+            current_line += char
+            if wait_for_nl:
+                if char == '\n':
+                    if current_line.strip() and current_column < column:
+                        res = ''.join(lines)
+                        return res, prefix[len(res):]
+
+                    lines.append(current_line)
+                    current_line = ""
+                    current_column = 0
+                    wait_for_nl = False
+            elif char in ' \t':
+                current_column += 1
+            elif char == '\n':
+                # unexpected empty line
+                current_column = 0
+            else:
+                # indent is finished
+                wait_for_nl = True
+        return ''.join(lines), current_line
+
+
+def _generate_pickle_name(gt, cache_dir=None):
     head, tail = os.path.splitext(gt)
     if tail == ".txt":
         tail = ""
     head, tail = os.path.splitext(gt)
     if tail == ".txt":
         tail = ""
-    return head + tail + ".".join(map(str, sys.version_info)) + ".pickle"
+    name = head + tail + ".".join(map(str, sys.version_info)) + ".pickle"
+    if cache_dir:
+        return os.path.join(cache_dir, os.path.basename(name))
+    else:
+        return name
 
 
 def load_grammar(gt="Grammar.txt", gp=None,
                  save=True, force=False, logger=None):
     """Load the grammar (maybe from a pickle)."""
     if logger is None:
 
 
 def load_grammar(gt="Grammar.txt", gp=None,
                  save=True, force=False, logger=None):
     """Load the grammar (maybe from a pickle)."""
     if logger is None:
-        logger = logging.getLogger()
+        logger = logging.getLogger(__name__)
     gp = _generate_pickle_name(gt) if gp is None else gp
     if force or not _newer(gp, gt):
         logger.info("Generating grammar tables from %s", gt)
     gp = _generate_pickle_name(gt) if gp is None else gp
     if force or not _newer(gp, gt):
         logger.info("Generating grammar tables from %s", gt)
@@ -152,7 +183,7 @@ def _newer(a, b):
     return os.path.getmtime(a) >= os.path.getmtime(b)
 
 
     return os.path.getmtime(a) >= os.path.getmtime(b)
 
 
-def load_packaged_grammar(package, grammar_source):
+def load_packaged_grammar(package, grammar_source, cache_dir=None):
     """Normally, loads a pickled grammar by doing
         pkgutil.get_data(package, pickled_grammar)
     where *pickled_grammar* is computed from *grammar_source* by adding the
     """Normally, loads a pickled grammar by doing
         pkgutil.get_data(package, pickled_grammar)
     where *pickled_grammar* is computed from *grammar_source* by adding the
@@ -164,8 +195,9 @@ def load_packaged_grammar(package, grammar_source):
 
     """
     if os.path.isfile(grammar_source):
 
     """
     if os.path.isfile(grammar_source):
-        return load_grammar(grammar_source)
-    pickled_name = _generate_pickle_name(os.path.basename(grammar_source))
+        gp = _generate_pickle_name(grammar_source, cache_dir) if cache_dir else None
+        return load_grammar(grammar_source, gp=gp)
+    pickled_name = _generate_pickle_name(os.path.basename(grammar_source), cache_dir)
     data = pkgutil.get_data(package, pickled_name)
     g = grammar.Grammar()
     g.loads(data)
     data = pkgutil.get_data(package, pickled_name)
     g = grammar.Grammar()
     g.loads(data)