Find lines where a word is located in all files under a folder.

find.py

__description__ = "Find lines where a word is defined in a folder."
__version__= "171115-1"
__author__= "Runsun Pan"

'''
>>> py find.py -h
usage: find.py [-h] [--version] [-f folder] [-p prefix] [-a activeModule]
               [-i includePrefix] [-x fileExt]
               word

Find lines where a word is defined in a folder. Runsun Pan

positional arguments:
  word              Target word or regex pattern string

optional arguments:
  -h, --help        show this help message and exit
  --version         Shows version and exits.
  -f folder         Target folder
  -p prefix         prefix. Could be a str in regexp form.
                    Default='function|module'
  -a activeModule   Search for modules that are set to run at this moment by
                    matching 'xxx(...);'. Useful for complex lib.
  -i includePrefix  Int. 1 = Include prefix defined in -p
  -x fileExt        Specifiy file extension like doc, py ... etc. Default:scad
  
  
Note: previous version was wrongfully dated as 2017.10.5 
      (should have been 2017.10.4)
      
Current ver 2017.10.4-2:
  -- more structural and clearer display
  -- output is grouped by file
  
ver 2017.10.4:      
This new version (2017.10.4) added couple options: prefix, file 
extension inclusion/exclusion, error handling. The target word to 
be search could be a string representation of python regexp pattern.

Example:

>>> py find.py getPlane -f scadx -i 0
+================================================================================
| Matches:
| scadx_geometry.scad:
|   #4769: function getPlaneByNormalLine(pq)=
|   #4780:     module getPlaneByNormalLine_demo()
|   #4783:         pl = getPlaneByNormalLine( pq );
|   #5362:     ? let( int= projPt( pt, getPlaneByNormalLine(pl)) )
|   #5365:     ? let( int= projPt( pt, getPlaneByNormalLine( [ORIGIN, pl])) )
|   #5400:     pl = expandPts( getPlaneByNormalLine(pq), 1);
|   #5427:     pl = expandPts( getPlaneByNormalLine( [ORIGIN, pt2]), 1);
| Untitled.scad:
|   #13: //getPlaneByNormalLine_demo();
+================================================================================
::: Matching re.compile('getPlane') in folder 'scadx':
::: Arguments Namespace(f='scadx', i=0, p='function|module', word='getPlane', x='scad')

Match 8 times in 2 files (see above for details):

scadx/scadx_geometry.scad: 7
scadx/Untitled.scad: 1

With 1 file errors:
(0)'scad_string.scad': UnicodeDecodeError: 'charmap' codec can't decode byte 0x8d in position 327: character maps to <undefined>


'''

import os, sys, re, argparse, traceback

# files with the following extentions are excluded
EXCLUDEFILES=["png","gif", "bmp", "lnk"]

# argument setup and parse
argp = argparse.ArgumentParser( 
       prog= __file__
       ,description=  __description__+ "\n" + __author__ )
argp.add_argument('--version', action='version'
                 , version='%(prog)s '+__version__ 
                 , help='Shows version and exits.')       
argp.add_argument("word", metavar="word", type=str, help="Target word or regex pattern string" )
argp.add_argument("-f", metavar="folder", type=str, default=".", help="Target folder")
argp.add_argument("-p", metavar="prefix", type=str, default="function|module"
                 , help="prefix. Could be a str in regexp form. Default='function|module'")
argp.add_argument("-a", metavar="activeModule", type=bool
                  , default=0
                  , help="Search for modules that are set to run at this moment by matching 'xxx(...);'. Useful for complex lib."
                  ) 
argp.add_argument("-i", metavar="includePrefix", type=int
                  , default=1
                  , help="Int. 1 = Include prefix defined in -p"
                  )

argp.add_argument('-x', metavar="fileExt", type=str, default="scad"
                 , help="Specifiy file extension like doc, py ... etc. Default:scad"
                 )     
                                               
args= argp.parse_args()


foldername = args.f 
word = args.word 

if args.a==True:
  ptn_str= "^\w*\([\w=\.\-,\[\] ]*\);"
elif args.i:
  ptn_str = "^("+args.p+") "+ "{0}".format(word) 
else:
  ptn_str = "{0}".format(word)
  
pattern = re.compile(ptn_str)  

#print("ptn_str: '%s'"%ptn_str)
print( '+'+"===="*20)
print('| Matches:')

mcount=0
fcount=0
errors = []
files = {}

def isValidFile( fn ):
  ''' Decide if a file is valid based on its extension '''
  if args.x:
     return fn.endswith("."+args.x)
  else:
     return not sum( [ fn.endswith("."+x) and 1 or 0 for x in EXCLUDEFILES ]) > 0 

 
for f in os.listdir( foldername ):
  if ( os.path.isfile(os.path.join(foldername, f)) and 
       isValidFile(f)
     ):
    fullpath = os.path.join(foldername, f)
    fcount=fcount+1
    thisFileHasMatches = False    
    try:
      lines = open(fullpath, "r").read().split("\n")
      for i,ln in enumerate(lines):
        if args.i==0:
           #match = word in ln or pattern.search("{0}".format(ln))
           match = pattern.search("{0}".format(ln))
           if match:
             if not thisFileHasMatches:
             	print("| "+f+":")
             	thisFileHasMatches = True
             mcount = mcount+1
             files.setdefault(fullpath,0)
             files[fullpath] += 1             	
             print( "|   #%s: %s "%(i, ln)) #.strip()) )
        else:
           #match = pattern.match(ln) or pattern.search("{0}".format(ln))
           match = pattern.search("{0}".format(ln))
           if match:
             if not thisFileHasMatches:
             	print("| "+f+":")
             	thisFileHasMatches = True
             mcount = mcount+1
             files.setdefault(fullpath,0)
             files[fullpath] += 1             	
             print( "|  #%s: %s "%(i, ln.strip()) )
    except:
      errors.append(
        "'%s': %s"%(f,traceback.format_exc().split("\n")[-2])      
      )
      
print('+'+'===='*20)
print( "::: Matching '%s' in folder '%s':"%('{0}'.format(ptn_str), foldername) )
print( "::: Arguments %s"%args )
print('\nMatch %s times in %s files (see above for details):\n'%( mcount
     , len(files.keys()) ))
print( '\n'.join( [ '%s: %s'%(x,y) for x,y in files.items() ] ) )          
print('\nWith %s file errors:'%( len(errors)) )
print( '\n'.join( [ "(%i)%s"%(i,x) for i,x in enumerate(errors)] ) )