Go to the documentation of this file.00001 import sys
00002 import os
00003 import re
00004 from BeautifulSoup import BeautifulSoup
00005
00006 BASE = "http://cmssdt.cern.ch/SDT/doxygen/"
00007 INDEX = {}
00008 printOutput = False;
00009
00010 def replace(regex,replacement,content):
00011 p = re.compile(regex,re.IGNORECASE);
00012 c = p.sub(replacement,content)
00013 return c
00014
00015 def findMatchingFiles(w, source_htmls):
00016 ret = ""
00017 for srcFile in source_htmls:
00018 if srcFile.split("/")[-1].__str__().find(w) != -1:
00019 ret += " " + srcFile
00020
00021 return ret
00022
00023 def filter(s,w,k):
00024 o = s.split()
00025 if len(o) > 1:
00026 betterChoice = ""
00027 for i in range(len(o)):
00028 if re.search("[^a-zA-Z]"+w+"[^a-zA-Z]", o[i]):
00029 if re.search(".*"+k+".*",o[i]):
00030 return o[i]
00031 else:
00032 if betterChoice == "" or len(betterChoice) > o[i]:
00033 betterChoice = o[i]
00034 return betterChoice
00035 else:
00036 if re.search("[^a-zA-Z]"+w+"[^a-zA-Z]", s):
00037 return s
00038 else:
00039 return ""
00040
00041 def getLink(word):
00042
00043 if word.isdigit() or (len(word) < 5):
00044 return ""
00045
00046 out = filter(findMatchingFiles(word, py_source_htmls),word,"")
00047 if not out or out == "":
00048 out = filter(findMatchingFiles(word, h_source_htmls),word,"")
00049 if not out or out == "":
00050 return ""
00051 return BASE+out.lstrip()
00052
00053 def process(filename):
00054
00055 if (filename != None) and (len(filename) < 5):
00056 return
00057
00058 fh = open(filename,'r')
00059 html = fh.read()
00060 fh.close()
00061
00062
00063 content = ""
00064
00065 soup = BeautifulSoup(html)
00066 pres = soup.findAll("pre", {"class":"fragment"})
00067
00068 for pre in pres:
00069 if pre.contents != None:
00070 content += pre.renderContents()
00071
00072
00073
00074 content = replace(r'<a\b[^>]*>(.*?)</a>','',content)
00075
00076 content = content.replace("'", "'")
00077 content = content.replace(""", '"')
00078
00079 matches = []
00080 tmp = re.findall('[\w,\.]+_cf[i,g,f]',content)
00081 for t in tmp:
00082 matches.extend(t.split("."))
00083
00084 matches.extend(re.findall('"\w+"',content))
00085 matches.extend(re.findall("'\w+'",content))
00086
00087 set = {}
00088 map(set.__setitem__, matches, [])
00089 matches = set.keys()
00090
00091 for match in matches:
00092
00093 match = match.replace("'", "")
00094 match = match.replace('"', "")
00095
00096 if (INDEX.has_key(match)):
00097 href = INDEX[match]
00098 else:
00099 href = getLink(match)
00100
00101 if (href != ""):
00102 INDEX[match] = BASE+href[href.find("CMSSW_"):]
00103
00104 link = "<a class=\"configfileLink\" href=\""+href+"\">"+match+"</a>"
00105 regex = r"\b"+match+r"\b"
00106 html = replace(regex, link, html)
00107
00108
00109 if printOutput:
00110 print ">>>>>["+match+"]",
00111
00112
00113
00114 if printOutput:
00115 print href
00116
00117
00118 fh = open(filename,'w')
00119 fh.write(html)
00120 fh.close()
00121
00122 if len(sys.argv) > 1:
00123
00124 DIR = sys.argv[1] +"/doc/html/"
00125
00126 global py_source_htmls
00127 global h_source_htmls
00128
00129 h_source_htmls = []
00130 py_source_htmls = []
00131
00132 print "ieskau h_source"
00133
00134 query = "find "+DIR+" -name '*8h_source.html' -print"
00135 output = os.popen(query)
00136 h_source_htmls = output.read().split("\n")
00137
00138 print "ieskau py_source"
00139
00140 query = "find "+DIR+" -name '*8py_source.html' -print"
00141 output = os.popen(query)
00142 py_source_htmls = output.read().split("\n")
00143
00144 query = 'find '+DIR+' \( -name "*cf[i,g,f]*py*html" -or -name "namespace*cf[i,g,f].html" \) -print '
00145 output = os.popen(query)
00146 files = output.read().split("\n")
00147 i = 0
00148 for file in files:
00149 i = i + 1
00150 print i.__str__()+") "+file
00151 process(file)
00152 print "-----------------------------------------------------------"
00153 else:
00154 print "not enough parameters"
1.7.3