Changeset 52 for branches/pyyaml3000/lib/yaml/scanner.py

Timestamp:

02/20/06 12:41:45 (7 years ago)

Author:

xi

Message:

Cleanup error messages.

File:

• branches/pyyaml3000/lib/yaml/scanner.py (modified) (10 diffs)

branches/pyyaml3000/lib/yaml/scanner.py

@@ -11 +11 @@
 __all__ = ['Scanner', 'ScannerError']
 
-from error import YAMLError
+from error import MarkedYAMLError
 from tokens import *
 
-class ScannerError(YAMLError):
-    # ScannerError: while reading a quoted string
-    #         in '...', line 5, column 10:
-    # key: "valu\?e"
-    #      ^
-    # got unknown quote character '?'
-    #         in '...', line 5, column 15:
-    # key: "valu\?e"
-    #            ^
-
-    def __init__(self, context=None, context_marker=None,
-            problem=None, problem_marker=None):
-        self.context = context
-        self.context_marker = context_marker
-        self.problem = problem
-        self.problem_marker = problem_marker
-
-    def __str__(self):
-        lines = []
-        for (place, marker) in [(self.context, self.context_marker),
-                                (self.problem, self.problem_marker)]:
-            if place is not None:
-                lines.append(place)
-                if marker is not None:
-                    lines.append(str(marker))
-        return '\n'.join(lines)
+class ScannerError(MarkedYAMLError):
+    pass
 
 class SimpleKey:
@@ -197 +173 @@
         if ch == u'.' and self.check_document_end():
             return self.fetch_document_end()
+
+        # TODO: support for BOM within a stream.
+        #if ch == u'\uFEFF':
+        #    return self.fetch_bom()    <-- issue BOMToken
 
         # Note: the order of the following checks is NOT significant.
@@ -750 +730 @@
         # specification requires. Any such mark will be considered as a part
         # of the document.
+        #
+        # TODO: We need to make tab handling rules more sane. A good rule is
+        #   Tabs cannot precede tokens
+        #   BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END,
+        #   KEY(block), VALUE(block), BLOCK-ENTRY
+        # So the checking code is
+        #   if <TAB>:
+        #       self.allow_simple_keys = False
+        # We also need to add the check for `allow_simple_keys == True` to
+        # `unwind_indent` before issuing BLOCK-END.
+        # Scanners for block, flow, and plain scalars need to be modified.
+
         if self.reader.index == 0 and self.reader.peek() == u'\uFEFF':
             self.reader.forward()
@@ -794 +786 @@
         if not length:
             raise ScannerError("while scanning a directive", start_marker,
-                    "expected directive name, but found %r" % ch.encode('utf-8'),
-                    self.reader.get_marker())
+                    "expected alphabetic or numeric character, but found %r"
+                    % ch.encode('utf-8'), self.reader.get_marker())
         value = self.reader.prefix(length)
         self.reader.forward(length)
         ch = self.reader.peek()
         if ch not in u'\0 \r\n\x85\u2028\u2029':
-            raise ScannerError("while scanning a directive" % name, start_marker,
+            raise ScannerError("while scanning a directive", start_marker,
                     "expected alphabetic or numeric character, but found %r"
                     % ch.encode('utf-8'), self.reader.get_marker())
@@ -812 +804 @@
         if self.reader.peek() != '.':
             raise ScannerError("while scanning a directive", start_marker,
-                    "expected a digit or '.', but found %r" % ch.encode('utf-8'),
+                    "expected a digit or '.', but found %r"
+                    % self.reader.peek().encode('utf-8'),
                     self.reader.get_marker())
         self.reader.forward()
@@ -818 +811 @@
         if self.reader.peek() not in u'\0 \r\n\x85\u2028\u2029':
             raise ScannerError("while scanning a directive", start_marker,
-                    "expected a digit or ' ', but found %r" % ch.encode('utf-8'),
+                    "expected a digit or ' ', but found %r"
+                    % self.reader.peek().encode('utf-8'),
                     self.reader.get_marker())
         return (major, minor)
@@ -849 +843 @@
         # See the specification for details.
         value = self.scan_tag_handle('directive', start_marker)
-        if self.reader.peek() != u' ':
+        ch = self.reader.peek()
+        if ch != u' ':
             raise ScannerError("while scanning a directive", start_marker,
                     "expected ' ', but found %r" % ch.encode('utf-8'),
@@ -903 +898 @@
         if not length:
             raise ScannerError("while scanning an %s" % name, start_marker,
-                    "expected anchor name, but found %r" % ch.encode('utf-8'),
-                    self.reader.get_marker())
+                    "expected alphabetic or numeric character, but found %r"
+                    % ch.encode('utf-8'), self.reader.get_marker())
         value = self.reader.prefix(length)
         self.reader.forward(length)
@@ -924 +919 @@
             suffix = self.scan_tag_uri('tag', start_marker)
             if self.reader.peek() != u'>':
-                raise ScannerError("while parsing a tag", start_marking,
-                        "expected '>', but got %r" % self.reader.peek().encode('utf-8'),
+                raise ScannerError("while parsing a tag", start_marker,
+                        "expected '>', but found %r" % self.reader.peek().encode('utf-8'),
                         self.reader.get_marker())
             self.reader.forward()
@@ -1310 +1305 @@
         # For some strange reasons, the specification does not allow '_' in
         # tag handles. I have allowed it anyway.
-        if self.reader.peek() != u'!':
+        ch = self.reader.peek()
+        if ch != u'!':
             raise ScannerError("while scanning a %s" % name, start_marker,
                     "expected '!', but found %r" % ch.encode('utf-8'),