update wow script to make it way better

2 files changed, 96 insertions, 32 deletions

diff --git a/python-template.py b/python-template.py
new file mode 100644
index 0000000..fda7a42
--- /dev/null
+++ b/python-template.py
@@ -0,0 +1,27 @@
+#!/usr/bin/python3
+
+import argparse
+import sys
+
+#this is a template for a python program that can be run from command line or used as a module
+
+def parseArgs():
+    parser = argparse.ArgumentParser(description='the program does a thing')
+    parser.add_argument('-v', '--verbose', action='store_true', help='verbose')
+    parser.add_argument('-i', '--input', type=str, required=True, help='input file')
+    parser.add_argument('-o', '--output', type=str, required=False, help='output file')
+    args = parser.parse_args()
+    return args
+
+def main():
+    args = parseArgs()
+    if args.verbose:
+        print(f"Input file: {args.input}")
+        if args.output:
+            print(f"Output file: {args.output}")
+    
+
+
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file
diff --git a/wow3.py b/wow3.py
index 03253b7..ac62eb0 100644..100755
--- a/wow3.py
+++ b/wow3.py
@@ -4,15 +4,21 @@ import argparse
 import sys
 import time
 import os
+import random
+import subprocess
+import chardet
+import filetype
 #Words Of Wisdom
 # output some random text from some given collection of files, 
 #   - primarily used to grab some random "words of wisdom" from my journals and writings
+#
 
 paths=[] #the paths to scan recursively for files from which to grab text
-samplefiles=[] #the paths of the individual files from which we want to grab text
+#samplefiles=[] #the paths of all the individual files from which we can grab text
 matchpattern='' #if we want to filter the files by some text pattern that the filename must match
 time_min = -1 #threshold time. dont use files that are older
 v=False
+
 def attemptReadSampleFile(filepath):
     if v: print('checking {}'.format(filepath))
     if os.path.isfile(filepath):
@@ -43,27 +49,11 @@ def attemptReadSampleFile(filepath):
     else: 
         if v: print('not a file')
         return None
-
-def parseArgs():
-    parser = argparse.ArgumentParser(description='output some random text from some given collection of files')
-    parser.add_argument('-v', '--verbose', action='store_true', help='verbose')
-    
-    parser.add_argument('-p', '--path', type=str, required=False, help='a path to scan', action='append', default=['~/doc'])
-    parser.add_argument('-o', '--output', type=str, required=False, help='output file')
-    args = parser.parse_args()
-    return args
-
-def main():
-    args = parseArgs()
-    if args.verbose:
-        print(f"Input file: {args.input}")
-        if args.output:
-            print(f"Output file: {args.output}")
-    
-    if args.path:
-        paths.append(args.path)
     
 
+def getSampleFiles(paths):
+    """grab all the possible sample files (recursive files from given paths)"""
+    samples = []
     tStart = time.time()
     for p in paths:
         if v: print('path {}'.format(p))
@@ -71,28 +61,75 @@ def main():
                 for root,dirs,files in os.walk(p):
                         if v: print('walk {}: {} files, {} dirs'.format(root, len(files), len(dirs)))
                         for f in files:
-                            samplefiles.append(root + '/' + f)
+                            samples.append(root + '/' + f)
         else:
-               samplefiles.append(p)
+               samples.append(p)
     tEnd = time.time()
     tDuration = tEnd - tStart
-    print('gathered {} candidate files in {} seconds, from paths {}'.format(len(samplefiles), tDuration, str(paths)))
-    #pick random file until we get an acceptable one
+    if v:
+        print('gathered {} candidate files in {} seconds, from paths {}'.format(len(samples), tDuration, str(paths)))
+    return samples
+    
+
+def getRandomFileTextContent(samplefiles):
+    """pick random file until we get an acceptable one
+        @return tuple(filename, textcontent)"""
     fi = random.randint(0, len(samplefiles))
-    t = attemptReadSampleFile(samplefiles[fi])
-    while t == None:
+    if v: print('candidate file: {}'.format(samplefiles[fi]))
+    t = attemptReadSampleFile(samplefiles[fi]) #check if valid file
+    while t == None: #this file was invalid, try again
         del samplefiles[fi]
         fi = random.randint(0, len(samplefiles))
         t = attemptReadSampleFile(samplefiles[fi])
+        if len(samplefiles) == 0: #no files are valid
+            return (None, None)
     
     mt = time.ctime(os.path.getmtime(samplefiles[fi]))
-    print('{} ;\n       last modified {} :\n  {}'.format(samplefiles[fi], mt, t))
+    if v: print('{} ;\n       last modified {} :\n '.format(samplefiles[fi], mt))
+    return (samplefiles[fi], t)
+
+#TODO params
+def getExcerpt(text):
+    """grab a random excerpt from the given stringh, which is assumed to be at least one paragraph length with multiple lines """
+    offset = random.randint(0,5)
+    lines = text.splitlines()
+    if offset >= len(lines)/2:
+        return text    
+    li = random.randint(offset, len(lines)-offset) #line index
+    res = '\n'.join(lines[li-offset: li+offset])
+    if len(res) < 7:
+        res = '\n'.join(lines)
+    return res
+
+
+def parseArgs():
+    global v
+    #get args from cmd line
+    parser = argparse.ArgumentParser(description='output some random text from some given collection of files')
+    parser.add_argument('-v', '--verbose', action='store_true', help='verbose')
+    
+    parser.add_argument('-p', '--paths', type=str, required=False, help='a path to scan', action='append', default=[])
+    parser.add_argument('-o', '--output', type=str, required=False, help='output file')
+    args = parser.parse_args()
+
+    if (args.verbose): v = True
+
+    if args.paths: paths.append(args.paths)
+
+    if len(paths) == 0: paths.append('./')
+
+    if v: print('using paths: {}'.format(paths))
+
+    return args
+
+def main():
+    args = parseArgs()
+    samplefiles = getSampleFiles(args.paths)
+    chosenfile = getRandomFileTextContent(samplefiles)
+    excerpt = getExcerpt(chosenfile[1])
+    print(excerpt)
+    print('\n - {}'.format(chosenfile[0]))
 
-    lines = t.splitlines()
-    li = random.randint(0, len(t)) #line index
-    #ci = random.randint(0, len(t)) #character index
-    res = '\n'.join(lines[li: li+7])
-    print(res)
 
 if __name__ == '__main__':
     main()
\ No newline at end of file