1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
#Copyright ReportLab Europe Ltd. 2000-2012
#see license.txt for license details
#history http://www.reportlab.co.uk/cgi-bin/viewcvs.cgi/public/reportlab/trunk/reportlab/tools/docco/yaml.py
# parses "Yet Another Markup Language" into a list of tuples.
# Each tuple says what the data is e.g.
# ('Paragraph', 'Heading1', 'Why Reportlab Rules')
# and the pattern depends on type.
"""
Parser for "Aaron's Markup Language" - a markup language
which is easier to type in than XML, yet gives us a
reasonable selection of formats.
The general rule is that if a line begins with a '.',
it requires special processing. Otherwise lines
are concatenated to paragraphs, and blank lines
separate paragraphs.
If the line ".foo bar bletch" is encountered,
it immediately ends and writes out any current
paragraph.
It then looks for a parser method called 'foo';
if found, it is called with arguments (bar, bletch).
If this is not found, it assumes that 'foo' is a
paragraph style, and the text for the first line
of the paragraph is 'bar bletch'. It would be
up to the formatter to decide whether on not 'foo'
was a valid paragraph.
Special commands understood at present are:
.image filename
- adds the image to the document
.beginPre Code
- begins a Preformatted object in style 'Code'
.endPre
- ends a preformatted object.
"""
import sys
import imp
from . import codegrab
#modes:
PLAIN = 1
PREFORMATTED = 2
BULLETCHAR = '\267' # assumes font Symbol, but works on all platforms
class Parser:
def __init__(self):
self.reset()
def reset(self):
self._lineNo = 0
self._style = 'Normal' # the default
self._results = []
self._buf = []
self._mode = PLAIN
def parseFile(self, filename):
#returns list of objects
data = open(filename, 'r').readlines()
for line in data:
#strip trailing newlines
self.readLine(line[:-1])
self.endPara()
return self._results
def readLine(self, line):
#this is the inner loop
self._lineNo = self._lineNo + 1
stripped = line.lstrip()
if len(stripped) == 0:
if self._mode == PLAIN:
self.endPara()
else: #preformatted, append it
self._buf.append(line)
elif line[0]=='.':
# we have a command of some kind
self.endPara()
words = stripped[1:].split()
cmd, args = words[0], words[1:]
#is it a parser method?
if hasattr(self.__class__, cmd):
#this was very bad; any type error in the method was hidden
#we have to hack the traceback
try:
getattr(self,cmd)(*args)
except TypeError as err:
sys.stderr.write("Parser method: %s(*%s) %s at line %d\n" % (cmd, tuple(args), err, self._lineNo))
raise
else:
# assume it is a paragraph style -
# becomes the formatter's problem
self.endPara() #end the last one
words = stripped.split(' ', 1)
assert len(words)==2, "Style %s but no data at line %d" % (words[0], self._lineNo)
(styletag, data) = words
self._style = styletag[1:]
self._buf.append(data)
else:
#we have data, add to para
self._buf.append(line)
def endPara(self):
#ends the current paragraph, or preformatted block
text = ' '.join(self._buf)
if text:
if self._mode == PREFORMATTED:
#item 3 is list of lines
self._results.append(('Preformatted', self._style,
'\n'.join(self._buf)))
else:
self._results.append(('Paragraph', self._style, text))
self._buf = []
self._style = 'Normal'
def beginPre(self, stylename):
self._mode = PREFORMATTED
self._style = stylename
def endPre(self):
self.endPara()
self._mode = PLAIN
def image(self, filename):
self.endPara()
self._results.append(('Image', filename))
def vSpace(self, points):
"""Inserts a vertical spacer"""
self._results.append(('VSpace', points))
def pageBreak(self):
"""Inserts a frame break"""
self._results.append(('PageBreak','blah')) # must be a tuple
def custom(self, moduleName, funcName):
"""Goes and gets the Python object and adds it to the story"""
self.endPara()
self._results.append(('Custom',moduleName, funcName))
def getModuleDoc(self, modulename, pathname=None):
"""Documents the entire module at this point by making
paragraphs and preformatted objects"""
docco = codegrab.getObjectsDefinedIn(modulename, pathname)
if docco.doc != None:
self._results.append(('Paragraph', 'DocString', docco.doc))
if len(docco.functions) > 0:
for fn in docco.functions:
if fn.status == 'official':
self._results.append(('Preformatted','FunctionHeader', fn.proto))
self._results.append(('Preformatted','DocString', fn.doc))
if len(docco.classes) > 0:
for cls in docco.classes:
if cls.status == 'official':
self._results.append(('Preformatted','FunctionHeader', 'Class %s:' % cls.name))
self._results.append(('Preformatted','DocString', cls.doc))
for mth in cls.methods:
if mth.status == 'official':
self._results.append(('Preformatted','FunctionHeader', mth.proto))
self._results.append(('Preformatted','DocStringIndent', mth.doc))
def getClassDoc(self, modulename, classname, pathname=None):
"""Documents the class and its public methods"""
docco = codegrab.getObjectsDefinedIn(modulename, pathname)
found = 0
for cls in docco.classes:
if cls.name == classname:
found = 1
self._results.append(('Preformatted','FunctionHeader', 'Class %s:' % cls.name))
self._results.append(('Preformatted','DocString', cls.doc))
for mth in cls.methods:
if mth.status == 'official':
self._results.append(('Preformatted','FunctionHeader', mth.proto))
self._results.append(('Preformatted','DocStringIndent', mth.doc))
break
assert found, 'No Classes Defined in ' + modulename
def nextPageTemplate(self, templateName):
self._results.append(('NextPageTemplate',templateName))
if __name__=='__main__': #NORUNTESTS
if len(sys.argv) != 2:
print('usage: yaml.py source.txt')
else:
p = Parser()
results = p.parseFile(sys.argv[1])
import pprint
pprint.pprint(results)
|
