Welcome, guest | Sign In | My Account | Store | Cart

This script allows to populate Cheetah text templates (http://www.cheetahtemplate.org/) with XML or CSV input data.

This is useful in my day2day work, where I often need to quickly generate bunch of files based on a templates and data.

Cheetah template are very easy to write and understand, and I find it easy to use with CSV or XML data.

Python, 272 lines
  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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
#!/usr/bin/python

import  getopt, sys

usage="""
    This script will populate a Cheetah template ((http://www.cheetahtemplate.org/) 
    with some input data (XML, CSV or JSON format).

    By default, the output is directed to stdout.

    USAGE:
        template [ -o outputFile ] [options] <template_file> <data_file> 
        template [-h/--help] 

    ARGUMENTS:
        <template_file> : Filename for the template file. Can be "stdin"
        <data_file> : Filename for input data. Can be "stdin"

    OPTIONS:
        -o <output file>   Direct output in a file instead of stdout.              
        -c 'commentChar'   Change the character used to begin comments in the template.
        -d 'directiveChar' Change the character used for directives in the template.
        -t XML|CSV         Input type (or guessed with file extension)

"""


def dieWith(msg) :
    sys.stderr.write(msg + '\n')
    sys.exit(-1)

# Enum of data type
TYPE_NONE = 0
TYPE_XML = 2
TYPE_CSV = 3

# Parse options
try:
    opts, args = getopt.getopt(sys.argv[1:], "hc:d:t:o:", ["help"])
except getopt.GetoptError :
    print usage

# Init arguments / options
compilerSettings = {}
inputType = TYPE_NONE
outFilename = None

# Switch on options
for opt, arg in opts:

    # Help
    if opt in ("-h", "--help") :
        print usage
        sys.exit(0)

    # Comment char
    elif opt == "-c" :
        compilerSettings['commentStartToken'] = arg

    # Directive char
    elif opt == "-d" :
        compilerSettings['directiveStartToken'] = arg

    # Output file
    elif opt == "-o" :
        outFilename = arg

    # Input type
    elif opt == "-t" :
        arg= arg.lower()
        if arg == "csv" :
            inputType = TYPE_CSV
        elif arg == "xml" :
            inputType = TYPE_XML
        else :
            dieWith("Invalid input type. Valid options are : CSV, XML")
            
# 2 mandatory arguments    
if len(args) != 2:
    print usage
    sys.exit(2);

(templateFile, dataFile) = args

# --------------------------------------------------------------------------
# XML to Python Object parser
# --------------------------------------------------------------------------
## {{{ http://code.activestate.com/recipes/534109/ (r8)
## Created by Wai Yip Tung on Sat, 13 Oct 2007 

import re
import xml.sax.handler

def xml2obj(src):
    """
    A simple function to converts XML data into native Python object.
    """

    non_id_char = re.compile('[^_0-9a-zA-Z]')
    def _name_mangle(name):
        return non_id_char.sub('_', name)

    class DataNode(object):
        def __init__(self):
            self._attrs = {}    # XML attributes and child elements
            self.data = None    # child text data
        def __len__(self):
            # treat single element as a list of 1
            return 1
        def __getitem__(self, key):
            if isinstance(key, basestring):
                return self._attrs.get(key,None)
            else:
                return [self][key]
        def __contains__(self, name):
            return self._attrs.has_key(name)
        def __nonzero__(self):
            return bool(self._attrs or self.data)
        def __getattr__(self, name):
            if name.startswith('__'):
                # need to do this for Python special methods???
                raise AttributeError(name)
            return self._attrs.get(name,None)
        def _add_xml_attr(self, name, value):
            if name in self._attrs:
                # multiple attribute of the same name are represented by a list
                children = self._attrs[name]
                if not isinstance(children, list):
                    children = [children]
                    self._attrs[name] = children
                children.append(value)
            else:
                self._attrs[name] = value
        def __str__(self):
            return self.data or ''
        def __repr__(self):
            items = sorted(self._attrs.items())
            if self.data:
                items.append(('data', self.data))
            return u'{%s}' % ', '.join([u'%s:%s' % (k,repr(v)) for k,v in items])

    class TreeBuilder(xml.sax.handler.ContentHandler):
        def __init__(self):
            self.stack = []
            self.root = DataNode()
            self.current = self.root
            self.text_parts = []
        def startElement(self, name, attrs):
            self.stack.append((self.current, self.text_parts))
            self.current = DataNode()
            self.text_parts = []
            # xml attributes --> python attributes
            for k, v in attrs.items():
                self.current._add_xml_attr(_name_mangle(k), v)
        def endElement(self, name):
            text = ''.join(self.text_parts).strip()
            if text:
                self.current.data = text
            if self.current._attrs:
                obj = self.current
            else:
                # a text only node is simply represented by the string
                obj = text or ''
            self.current, self.text_parts = self.stack.pop()
            self.current._add_xml_attr(_name_mangle(name), obj)
        def characters(self, content):
            self.text_parts.append(content)

    builder = TreeBuilder()
    if isinstance(src,basestring):
        xml.sax.parseString(src, builder)
    else:
        xml.sax.parse(src, builder)
    return builder.root._attrs.values()[0]

## end of http://code.activestate.com/recipes/534109/ }}}




# -------------------------------------------------
# Read input data file
# -------------------------------------------------

# Open input file
import csv
if dataFile == "stdin" :
    file = sys.stdin
else:
    file = open(dataFile);
        
    # Guess input type if not set in options
    if inputType == TYPE_NONE :
        import os.path as path
        ext = path.splitext(dataFile)[1].lower()

        if ext == '.csv' :
            inputType = TYPE_CSV
        elif ext == '.xml' :
            inputType = TYPE_XML 
        elif ext == '.json' :
            inputType = TYPE_JSON

# Switch on input type
if inputType == TYPE_NONE :
    dieWith("No input data type specified. Failed to guess it.")

# CSV
elif inputType == TYPE_CSV :

    reader = csv.DictReader(file, delimiter=";")

    # Almost empty 
    class Container :
        def __init__(self) :
            self.lines= []

    data = Container()

    # Loop on lines
    for line in reader:

        data.lines.append(line)

        # Loop on values of the line
        for key, value in line.items() :
           
            # Does it exists yet in "data"
            if data.__dict__.has_key(key) :
                # Then happend it
                data.__dict__[key].append(value)
            else :
                # Create a list 
                data.__dict__[key] = [value]

    # Make 'columns' accessible as a global name in the template
    data.columns = reader.fieldnames

# XML
elif inputType == TYPE_XML :
    
    # Transform XML into Python object
    data = xml2obj(file)

else :
    dieWith('Input data type not supported')

# --------------------------------------------
# Read template
# --------------------------------------------

from Cheetah.Template import Template
if templateFile == 'stdin' :
    file = sys.stdin
else:
    file = open(templateFile)

template = Template(
    file=file, 
    searchList=[data], # Attach data
    compilerSettings = compilerSettings)

# -------------------------------------------
# Output result
# -------------------------------------------

if outFilename == None :
    out = sys.stdout
else :
    out = open(outFilename, 'w')

out.write(str(template))

Usage

Here is the usage of this script.

USAGE:
   
template [ -o outputFile ] [options] <template_file> <data_file>
   
template [-h/--help]

ARGUMENTS
:
   
<template_file> : Filename for the template file. Can be "stdin"
   
<data_file> : Filename for input data. Can be "stdin"

OPTIONS
:
   
-o <output file>   Set the output file (stdout by default)
   
-c 'commentChar'   Change the character used to begin comments in the template.
   
-d 'directiveChar' Change the character used for directives in the template.
   
-t XML|CSV         Input type (or guessed with input file extension)

XML input data

Here is a example of a template file :

#for $currContact in $contact

   
Name : $currContact.firstName $currContact.name
   
Tel: #echo ', '.join(map(lambda number : '%s (%s)' % (number, number.type), $currContact.number))
   
Emails:
       
#for $email in $currContact.email
            $email
.type : $email
       
#end for

#end for

And its associated input file :

<address-book>
   
<contact firstName="John" name="Doh" >
       
<address>10, Red Street. 088990 SpringField</address>
       
<email type="work" >john.doh@gmail.com</email>
       
<email type="personal" >john.doh@hotmail.com</email>
       
<number type="work">0102030506</number>
       
<number type="mobile">0506030506</number>
   
</contact>

   
<contact firstName="Barak" name="Obama" >
       
<address>White House, Washington</address>
       
<email type="work" >barak.obama@whitehouse.com</email>
       
<email type="personal" >barak.obama@hotmail.com</email>
       
<number type="work">0102030506</number>
   
</contact>
</address-book>

And here is the result output :

Name : John Doh
Tel: 0102030506 (work), 0506030506 (mobile)
Emails:
        work
: john.doh@gmail.com
        personal
: john.doh@hotmail.com


Name : Barak Obama
Tel: 0102030506 (work)
Emails:
        work
: barak.obama@whitehouse.com
        personal
: barak.obama@hotmail.com

CSV input data

CSV files should use semi-colon separator ';'. They should contain one line of header, giving the names of the columns. Then, from the template, the lines of data are accessed by the global variable "$lines" and the list of columns is accessed by the global variable "$columns". For each line, the value for a specific column can be accessed accessed either by "$line.columnName" or "$line['columnName']".

Here is an example of a template written for CSV data :

#for $line in $lines
   
Name  : $line.firstName $line.name
   
Tel   : $line.tel
   
Email : $line.email
   
Address :
        $line
.address

#end for

And the corresponding CSV input data :

firstName;name;address;tel;email
Barack;Obama;White house;01020304;barack.oabama@whitehouse.com
John;Doh;Springfield;99999999;john.doe@hotmail.com

And here is the result :

Name  : Barack Obama
Tel   : 01020304
Email : barack.oabama@whitehouse.com
Address :
   
White house

Name  : John Doh
Tel   : 99999999
Email : john.doe@hotmail.com
Address :
   
Springfiel