This Text file is old! In a 🏛️Museum, an unsorted archive of (user-)pages. (Saved from Geocities in Oct-2009. The archival story: oocities.org)
--------------------------------------- (To 🚫report any bad content: archivehelp @ gmail.com)

# getrefs1 - 
# get all references to a name in the files of a directory and write
# each file line with a reference out to a file.  

# given a directory and a regular expression representing
# all the different forms of a name to search for,
# iterate over the directory opening each file then
# reading it line by line trying to match the regex on the line,
# if it matches then write the match out to the references file
# which includes the file name, the line number within the file,
# the character offset of the regex match within the line,
# and the contents of the whole line.

#brcrc10.txt(1343,32):line

import glob, re, string, sys, os.path

#----------------------------------------------------------------------

def get_references_infile(dir,file,name,matches):
    # open file, read through all the lines, add matches to list
    #print "file: ", file  
    filename = dir + file
    infile = open(filename,'r')
    lineno = 0
    re_name = re.compile("(%s)" % (name),re.IGNORECASE)
    for line in infile.readlines(): 
        lineno = lineno + 1
        match = re.search(re_name,line)
        if match:
           span = match.span(0)
           charno = span[0] + 1 
           line = string.rstrip(line)
           match_record = "%s(%s,%s):%s" % (filename,lineno,charno,line)
           #print match_record
           matches.append(match_record)
    infile.close()

def get_references_indirectory(dir,name):
    matches = []
    # get all the files in the directory
    allfiles = dir + '*.*'
    fileset = glob.glob(allfiles)
    # iterate over each file
    for path in fileset:
        pathsplit = os.path.split(path)
        file = pathsplit[1]
        get_references_infile(dir,file,name,matches)
    return matches

#----------------------------------------------------------------------
# main program:

if __name__ == "__main__":
   if len(sys.argv) != 3:
      #print "Usage: ", sys.argv[0], "directory name_regex"
      dir  = "c:\\Balzac\\balzacbooksnofront\\"
      name = "Bianchon"
      print "----------Find '%s' in files-----" % (name)
      matches = get_references_indirectory(dir,name) 
      for match in matches:
          print match
      print "%s occurences have been found" % (len(matches))
   else:
      dir  = sys.argv[1] 
      name = sys.argv[2]
      matches = get_references_indirectory(dir,name)