Initial Commit
[bus.git] / openlayers / tools / exampleparser.py
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
#!/usr/bin/env python
 
import sys
import os
import re
import urllib2
import time
from xml.dom.minidom import Document
 
try:
    import xml.etree.ElementTree as ElementTree 
except ImportError:
    try:
        import cElementTree as ElementTree
    except ImportError:
        try:
            import elementtree.ElementTree as ElementTree
        except ImportError:
            import lxml.etree as ElementTree
 
missing_deps = False
try:
    import simplejson
    from BeautifulSoup import BeautifulSoup
except ImportError, E:
    missing_deps = E 
 
feedName = "example-list.xml"
feedPath = "http://openlayers.org/dev/examples/"
 
def getListOfOnlineExamples(baseUrl):
    """
    useful if you want to get a list of examples a url. not used by default.
    """
    html = urllib2.urlopen(baseUrl)
    soup = BeautifulSoup(html)
    examples = soup.findAll('li')
    examples = [example.find('a').get('href') for example in examples]
    examples = [example for example in examples if example.endswith('.html')]
    examples = [example for example in examples]
    return examples
    
def getListOfExamples(relPath):
    """
    returns list of .html filenames within a given path - excludes example-list.html
    """
    examples = os.listdir(relPath)
    examples = [example for example in examples if example.endswith('.html') and example != "example-list.html"]
    return examples
    
 
def getExampleHtml(location):
    """
    returns html of a specific example that is available online or locally
    """
    print '.',
    if location.startswith('http'):
        return urllib2.urlopen(location).read()
    else:
        f = open(location)
        html = f.read()
        f.close()
        return html
        
    
def extractById(soup, tagId, value=None):
    """
    returns full contents of a particular tag id
    """
    beautifulTag = soup.find(id=tagId)
    if beautifulTag:
        if beautifulTag.contents: 
            value = str(beautifulTag.renderContents()).strip()
            value = value.replace('\t','')
            value = value.replace('\n','')
    return value
 
def getRelatedClasses(html):
    """
    parses the html, and returns a list of all OpenLayers Classes 
    used within (ie what parts of OL the javascript uses).  
    """
    rawstr = r'''(?P<class>OpenLayers\..*?)\('''
    return re.findall(rawstr, html)
 
def parseHtml(html,ids):
    """
    returns dictionary of items of interest
    """
    soup = BeautifulSoup(html)
    d = {}
    for tagId in ids:
        d[tagId] = extractById(soup,tagId)
    #classes should eventually be parsed from docs - not automatically created.
    classes = getRelatedClasses(html)
    d['classes'] = classes
    return d
 
def getSvnInfo(path):
    h = os.popen("svn info %s --xml" % path)
    tree = ElementTree.fromstring(h.read())
    h.close()
    d = {
        'url': tree.findtext('entry/url'),
        'author': tree.findtext('entry/commit/author'),
        'date': tree.findtext('entry/commit/date')
    }
    return d
    
def createFeed(examples):
    doc = Document()
    atomuri = "http://www.w3.org/2005/Atom"
    feed = doc.createElementNS(atomuri, "feed")
    feed.setAttribute("xmlns", atomuri)
    title = doc.createElementNS(atomuri, "title")
    title.appendChild(doc.createTextNode("OpenLayers Examples"))
    feed.appendChild(title)
    link = doc.createElementNS(atomuri, "link")
    link.setAttribute("rel", "self")
    link.setAttribute("href", feedPath + feedName)
    
    modtime = time.strftime("%Y-%m-%dT%I:%M:%SZ", time.gmtime())
    id = doc.createElementNS(atomuri, "id")
    id.appendChild(doc.createTextNode("%s%s#%s" % (feedPath, feedName, modtime)))
    feed.appendChild(id)
    
    updated = doc.createElementNS(atomuri, "updated")
    updated.appendChild(doc.createTextNode(modtime))
    feed.appendChild(updated)
 
    examples.sort(key=lambda x:x["modified"])
    for example in sorted(examples, key=lambda x:x["modified"], reverse=True):
        entry = doc.createElementNS(atomuri, "entry")
        
        title = doc.createElementNS(atomuri, "title")
        title.appendChild(doc.createTextNode(example["title"] or example["example"]))
        entry.appendChild(title)
        
        link = doc.createElementNS(atomuri, "link")
        link.setAttribute("href", "%s%s" % (feedPath, example["example"]))
        entry.appendChild(link)
    
        summary = doc.createElementNS(atomuri, "summary")
        summary.appendChild(doc.createTextNode(example["shortdesc"] or example["example"]))
        entry.appendChild(summary)
        
        updated = doc.createElementNS(atomuri, "updated")
        updated.appendChild(doc.createTextNode(example["modified"]))
        entry.appendChild(updated)
        
        author = doc.createElementNS(atomuri, "author")
        name = doc.createElementNS(atomuri, "name")
        name.appendChild(doc.createTextNode(example["author"]))
        author.appendChild(name)
        entry.appendChild(author)
        
        id = doc.createElementNS(atomuri, "id")
        id.appendChild(doc.createTextNode("%s%s#%s" % (feedPath, example["example"], example["modified"])))
        entry.appendChild(id)
        
        feed.appendChild(entry)
 
    doc.appendChild(feed)
    return doc    
    
def wordIndex(examples):
    """
    Create an inverted index based on words in title and shortdesc.  Keys are
    lower cased words.  Values are dictionaries with example index keys and
    count values.
    """
    index = {}
    unword = re.compile("\\W+")
    keys = ["shortdesc", "title"]
    for i in range(len(examples)):
        for key in keys:
            text = examples[i][key]
            if text:
                words = unword.split(text)
                for word in words:
                    if word:
                        word = word.lower()
                        if index.has_key(word):
                            if index[word].has_key(i):
                                index[word][i] += 1
                            else:
                                index[word][i] = 1
                        else:
                            index[word] = {i: 1}
    return index
    
if __name__ == "__main__":
 
    if missing_deps:
        print "This script requires simplejson and BeautifulSoup. You don't have them. \n(%s)" % E
        sys.exit()
    
    if len(sys.argv) > 1:
        outFile = open(sys.argv[1],'w')
    else:
        outFile = open('../examples/example-list.js','w')
    
    examplesLocation = '../examples'
    print 'Reading examples from %s and writing out to %s' % (examplesLocation, outFile.name)
   
    exampleList = []
    docIds = ['title','shortdesc']
   
    #comment out option to create docs from online resource
    #examplesLocation = 'http://svn.openlayers.org/sandbox/docs/examples/'
    #examples = getListOfOnlineExamples(examplesLocation)
 
    examples = getListOfExamples(examplesLocation)
 
    modtime = time.strftime("%Y-%m-%dT%I:%M:%SZ", time.gmtime())
 
    for example in examples:
        url = os.path.join(examplesLocation,example)
        html = getExampleHtml(url)
        tagvalues = parseHtml(html,docIds)
        tagvalues['example'] = example
        # add in svn info
        d = getSvnInfo(url)
        tagvalues["modified"] = d["date"] or modtime
        tagvalues["author"] = d["author"] or "anonymous"
        tagvalues['link'] = example
 
        exampleList.append(tagvalues)
        
    print
    
    exampleList.sort(key=lambda x:x['example'].lower())
    
    index = wordIndex(exampleList)
 
    json = simplejson.dumps({"examples": exampleList, "index": index})
    #give the json a global variable we can use in our js.  This should be replaced or made optional.
    json = 'var info=' + json 
    outFile.write(json)
    outFile.close()
 
    print "writing feed to ../examples/%s " % feedName
    atom = open('../examples/%s' % feedName, 'w')
    doc = createFeed(exampleList)
    atom.write(doc.toxml())
    atom.close()
 
 
    print 'complete'