1. rcrnstn/xdot.py
  2. xdot
  3. dot
  4. scanner.py
Browse code

Fix identation.

Fixes https://github.com/jrfonseca/xdot.py/issues/73

Jose Fonseca authored on 04/01/2020 11:41:20
Showing 1 changed files
xdot/dot/scanner.py
History View file @ f762c39
... ... 
@@ -54,11 +54,11 @@ class Scanner:
54 54 
         flags = re.DOTALL
55 55 
         if self.ignorecase:
56 56 
             flags |= re.IGNORECASE
57 
-            self.tokens_re = re.compile(
58 
-                b'|'.join([b'(' + regexp + b')'
59 
-                           for type, regexp, test_lit in self.tokens]),
60 
-                flags
61 
-            )
57 
+        self.tokens_re = re.compile(
58 
+            b'|'.join([b'(' + regexp + b')'
59 
+                       for type, regexp, test_lit in self.tokens]),
60 
+            flags
61 
+        )
62 62
63 63 
     def next(self, buf, pos):
64 64 
         if pos >= len(buf):
Browse code

Fix most flake8 errors

Peter Hill authored on 02/07/2016 10:27:27 • Jose Fonseca committed on 10/07/2016 08:40:15
Showing 1 changed files
xdot/dot/scanner.py
History View file @ 0d30b93
... ... 
@@ -54,10 +54,11 @@ class Scanner:
54 54 
         flags = re.DOTALL
55 55 
         if self.ignorecase:
56 56 
             flags |= re.IGNORECASE
57 
-        self.tokens_re = re.compile(
58 
-            b'|'.join([b'(' + regexp + b')' for type, regexp, test_lit in self.tokens]),
59 
-             flags
60 
-        )
57 
+            self.tokens_re = re.compile(
58 
+                b'|'.join([b'(' + regexp + b')'
59 
+                           for type, regexp, test_lit in self.tokens]),
60 
+                flags
61 
+            )
61 62
62 63 
     def next(self, buf, pos):
63 64 
         if pos >= len(buf):
... ... 
@@ -71,7 +72,7 @@ class Scanner:
71 72 
                 type = self.literals.get(text, type)
72 73 
             return type, text, pos
73 74 
         else:
74 
-            c = buf[pos : pos + 1]
75 
+            c = buf[pos:pos+1]
75 76 
             return self.symbols.get(c, None), c, pos + 1
76 77
77 78
... ... 
@@ -81,11 +82,11 @@ class DotScanner(Scanner):
81 82 
     tokens = [
82 83 
         # whitespace and comments
83 84 
         (SKIP,
84 
-            br'[ \t\f\r\n\v]+|'
85 
-            br'//[^\r\n]*|'
86 
-            br'/\*.*?\*/|'
87 
-            br'#[^\r\n]*',
88 
-        False),
85 
+         br'[ \t\f\r\n\v]+|'
86 
+         br'//[^\r\n]*|'
87 
+         br'/\*.*?\*/|'
88 
+         br'#[^\r\n]*',
89 
+         False),
89 90
90 91 
         # Alphanumeric IDs
91 92 
         (ID, br'[a-zA-Z_\x80-\xff][a-zA-Z0-9_\x80-\xff]*', True),
Browse code

Cleaner splitting into separate modules

Peter Hill authored on 02/07/2016 09:45:05 • Jose Fonseca committed on 10/07/2016 08:40:15
Showing 1 changed files
xdot/dot/scanner.py
History View file @ f0f0326
1 1 
new file mode 100644
... ... 
@@ -0,0 +1,129 @@
1 
+# Copyright 2008-2015 Jose Fonseca
2 
+#
3 
+# This program is free software: you can redistribute it and/or modify it
4 
+# under the terms of the GNU Lesser General Public License as published
5 
+# by the Free Software Foundation, either version 3 of the License, or
6 
+# (at your option) any later version.
7 
+#
8 
+# This program is distributed in the hope that it will be useful,
9 
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
10 
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
11 
+# GNU Lesser General Public License for more details.
12 
+#
13 
+# You should have received a copy of the GNU Lesser General Public License
14 
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
15 
+#
16 
+import re
17 
+
18 
+EOF = -1
19 
+SKIP = -2
20 
+
21 
+ID = 0
22 
+STR_ID = 1
23 
+HTML_ID = 2
24 
+EDGE_OP = 3
25 
+
26 
+LSQUARE = 4
27 
+RSQUARE = 5
28 
+LCURLY = 6
29 
+RCURLY = 7
30 
+COMMA = 8
31 
+COLON = 9
32 
+SEMI = 10
33 
+EQUAL = 11
34 
+PLUS = 12
35 
+
36 
+STRICT = 13
37 
+GRAPH = 14
38 
+DIGRAPH = 15
39 
+NODE = 16
40 
+EDGE = 17
41 
+SUBGRAPH = 18
42 
+
43 
+
44 
+class Scanner:
45 
+    """Stateless scanner."""
46 
+
47 
+    # should be overriden by derived classes
48 
+    tokens = []
49 
+    symbols = {}
50 
+    literals = {}
51 
+    ignorecase = False
52 
+
53 
+    def __init__(self):
54 
+        flags = re.DOTALL
55 
+        if self.ignorecase:
56 
+            flags |= re.IGNORECASE
57 
+        self.tokens_re = re.compile(
58 
+            b'|'.join([b'(' + regexp + b')' for type, regexp, test_lit in self.tokens]),
59 
+             flags
60 
+        )
61 
+
62 
+    def next(self, buf, pos):
63 
+        if pos >= len(buf):
64 
+            return EOF, b'', pos
65 
+        mo = self.tokens_re.match(buf, pos)
66 
+        if mo:
67 
+            text = mo.group()
68 
+            type, regexp, test_lit = self.tokens[mo.lastindex - 1]
69 
+            pos = mo.end()
70 
+            if test_lit:
71 
+                type = self.literals.get(text, type)
72 
+            return type, text, pos
73 
+        else:
74 
+            c = buf[pos : pos + 1]
75 
+            return self.symbols.get(c, None), c, pos + 1
76 
+
77 
+
78 
+class DotScanner(Scanner):
79 
+
80 
+    # token regular expression table
81 
+    tokens = [
82 
+        # whitespace and comments
83 
+        (SKIP,
84 
+            br'[ \t\f\r\n\v]+|'
85 
+            br'//[^\r\n]*|'
86 
+            br'/\*.*?\*/|'
87 
+            br'#[^\r\n]*',
88 
+        False),
89 
+
90 
+        # Alphanumeric IDs
91 
+        (ID, br'[a-zA-Z_\x80-\xff][a-zA-Z0-9_\x80-\xff]*', True),
92 
+
93 
+        # Numeric IDs
94 
+        (ID, br'-?(?:\.[0-9]+|[0-9]+(?:\.[0-9]*)?)', False),
95 
+
96 
+        # String IDs
97 
+        (STR_ID, br'"[^"\\]*(?:\\.[^"\\]*)*"', False),
98 
+
99 
+        # HTML IDs
100 
+        (HTML_ID, br'<[^<>]*(?:<[^<>]*>[^<>]*)*>', False),
101 
+
102 
+        # Edge operators
103 
+        (EDGE_OP, br'-[>-]', False),
104 
+    ]
105 
+
106 
+    # symbol table
107 
+    symbols = {
108 
+        b'[': LSQUARE,
109 
+        b']': RSQUARE,
110 
+        b'{': LCURLY,
111 
+        b'}': RCURLY,
112 
+        b',': COMMA,
113 
+        b':': COLON,
114 
+        b';': SEMI,
115 
+        b'=': EQUAL,
116 
+        b'+': PLUS,
117 
+    }
118 
+
119 
+    # literal table
120 
+    literals = {
121 
+        b'strict': STRICT,
122 
+        b'graph': GRAPH,
123 
+        b'digraph': DIGRAPH,
124 
+        b'node': NODE,
125 
+        b'edge': EDGE,
126 
+        b'subgraph': SUBGRAPH,
127 
+    }
128 
+
129 
+    ignorecase = True