improve generate.pyHEADmaster

* Add ability to choose subdir name format.
* Add day (D) as a variable to use.
* Add ability to use other exif date tags, and filename, to determine
the date to use. Timestamp is a last-resort option only!
* Change output of the cli equivalent actions to stdout (from stderr).

1 files changed, 105 insertions, 24 deletions

diff --git a/genlib.py b/genlib.py
index 898542d..62676ad 100644
--- a/genlib.py
+++ b/genlib.py
@@ -6,12 +6,15 @@
 #    https://stackoverflow.com/questions/1192978/python-get-relative-path-of-all-files-and-subfolders-in-a-directory
 #    https://stackoverflow.com/questions/3207219/how-do-i-list-all-files-of-a-directory
 #    https://stackoverflow.com/questions/600268/mkdir-p-functionality-in-python
+# Improve:
+#    store as a variable the method used to determine date. String, from options ['exif datetimeoriginal','filename','timestamp'] or similar.
 from sys import stderr
 from exifread import process_file
 from os import walk, path, stat, symlink
 from pathlib import Path
 from datetime import date
 from shutil import copy2, move
+from re import compile as re_compile
 
 try:
    if debuglevel is None:
@@ -19,10 +22,32 @@ try:
 except:
    debuglevel = 0
 
+# Sorry, don't care about anything other than 1900s and forward. We also benefit from relying on full-width month and day fields.
+dateregex = re_compile("(?P<year>(19|2[0-9])[0-9]{2})(?P<separator>[\.-]?)(?P<month>[01][0-9])(?P=separator)(?P<day>[03][0-9])")
+
 # Functions
 def eprint(*args, **kwargs):
    print(*args, file=stderr, **kwargs)
 
+# this function is for manual debugging only
+def list_all_tags(tf):
+   tags = []
+   try:
+      with open(tf,'rb') as f:
+         tags = process_file(f,details=True)
+   except:
+      eprint(f"Failed to process tags for {tf}")
+      pass
+   for t in tags:
+      try:
+         if "JPEGThumbnail" in t:
+            o = tags[t][:40] # first 40 bytes
+         else:
+            o = tags[t]
+         print(f'{t}: {o}')
+      except:
+         print(f'Failed to print {t}')
+
 def list_files(indir,relative=False,debuglevel=debuglevel, excludes=None):
    x = 0
    f = []
@@ -62,45 +87,96 @@ def limit(listf=None,filters=["image","video"]):
          newlist.append(f)
    return newlist
 
-def get_file_YM(tf,debuglevel=debuglevel,zero_pad=False):
-   Y = 0 ; M = 0
+def get_file_YMD(tf,debuglevel=debuglevel,zero_pad=False):
+   Y = 0 ; M = 0 ; D = 0
    #eprint(f"Debuglevel {debuglevel}")
    try:
       # read exif data
       with open(tf,'rb') as f:
-         tags = process_file(f, details=False, stop_tag="Image DateTime")
+         tags = process_file(f, details=False) #, stop_tag="Image DateTime")
+      # prefer Image DateTime
       if "Image DateTime" in tags:
          #if debuglevel >= 5: eprint(tf,tags["Image DateTime"])
          Y = str(tags["Image DateTime"]).split(' ')[0].split(':')
-         if Y == "['']" or Y == ['']:
-            Y = ['0','0']
-         M = Y[1] ; Y = Y[0];
+      elif "EXIF DateTimeOriginal" in tags:
+         Y = str(tags["EXIF DateTimeOriginal"]).split(' ')[0].split(':')
+      if Y == "['']" or Y == ['']:
+         Y = ['0','0','0']
+      M = Y[1] ; D = Y[2] ; Y = Y[0];
       # Any other image timestamps could be used here
       #eprint(tags)
    except KeyboardInterrupt:
-      return -1, -1
+      return -1, -1, -1
    except:
       if debuglevel >= 1: eprint(f"Unable to extract any exif data for {tf}")
-   if int(Y) == 0 or int(M) == 0:
-      # need to just use timestamp
+   #print(f"Y={Y} M={M} D={D}")
+
+   use_fn = False
+   try:
+      if int(Y) == 0 or int(M) == 0 or int(D) == 0:
+         use_fn = True
+   except:
+      use_fn = True
+   # try to use filename to look for YYYYMMDD or YYYY.MM.DD (pseudoregex) pattern
+   if use_fn:
+      fn = path.basename(tf)
+      try:
+         match = dateregex.search(fn)
+         #print(f"match={match.group()}")
+         # Remove any separators. These two are hardcoded in the global dateregex
+         match1 = match.group().replace("-","").replace(".","")
+         Y = str(match1)[:4]
+         M = str(match1)[4:6]
+         D = str(match1)[6:8]
+         #print(f"Y={Y} M={M} D={D}")
+      except:
+         if debuglevel >=1: eprint(f"Unable to determine date from filename {tf}")
+
+   # Determine if we need to use the timestamp
+   use_ts = False
+   try:
+      if int(Y) == 0 or int(M) == 0 or int(D) == 0:
+         use_ts = True
+   except:
+      use_ts = True
+   if use_ts:
+      if debuglevel >= 9: eprint("Using timestamp...")
+      # need to just use timestamp, which is really a last resort
       try:
          ts = date.fromtimestamp(stat(tf).st_mtime)
       except KeyboardInterrupt:
-         return -1, -1
+         return -1, -1, -1
       except:
          # no timestamp available from filesystem?
          if debuglevel >= 1: eprint(f"No timestamp available for {tf}")
-      if int(Y) == 0: Y = ts.year
-      if int(M) == 0: M = ts.month
+      use_ts_y=False ; use_ts_m=False ; use_ts_d=False
+      try:
+         if int(Y) == 0: use_ts_y=True
+      except:
+         use_ts_y=True
+      try:
+         if int(M) == 0: use_ts_m=True
+      except:
+         use_ts_m=True
+      try:
+         if int(D) == 0: use_ts_d=True
+      except:
+         use_ts_d=True
+      if use_ts_y: Y = ts.year
+      if use_ts_m: M = ts.month
+      if use_ts_d: D = ts.day
+
    if zero_pad:
       M = str(M).zfill(2)
+      D = str(D).zfill(2)
    else:
       M = str(int(M))
+      D = str(int(D))
    if debuglevel >= 3:
-      eprint(f"{tf} {Y}/{M}")
-   return Y, M
+      eprint(f"{tf} {Y}/{M}/{D}")
+   return Y, M, D
 
-def make_YM_forest(outdir, flist, action = "symlink", dryrun=True, debuglevel=debuglevel, zero_pad=False, relative_symlinks = False):
+def make_forest(outdir, flist, subdirformat = "{Y}/{M}", action = "symlink", dryrun=True, debuglevel=debuglevel, zero_pad=False, relative_symlinks = False):
    """
    For each file in flist, [action] it to outdir, sorting into YYYY/MM subdirs based on exif metadata or timestamp.
    Action may be one of ['symlink', 'copy', 'move'].
@@ -111,7 +187,7 @@ def make_YM_forest(outdir, flist, action = "symlink", dryrun=True, debuglevel=de
 
    # validate input
    if action not in ['symlink', 'copy', 'move']:
-      eprint("make_YM_forest action may be one of ['symlink', 'copy', 'move'].")
+      eprint("make_forest action may be one of ['symlink', 'copy', 'move'].")
       return -1
 
    # Learn all directories to make
@@ -120,7 +196,7 @@ def make_YM_forest(outdir, flist, action = "symlink", dryrun=True, debuglevel=de
    destdirs = []
    for f in flist:
       try:
-         Y, M = get_file_YM(f,debuglevel=debuglevel,zero_pad=zero_pad)
+         Y, M, D = get_file_YMD(f,debuglevel=debuglevel,zero_pad=zero_pad)
          if Y == -1 and M == -1:
             #eprint("Stopping due to keyboard variant 2.")
             stop = True
@@ -131,11 +207,16 @@ def make_YM_forest(outdir, flist, action = "symlink", dryrun=True, debuglevel=de
          break
       if zero_pad:
          M = str(M).zfill(2)
+         D = str(D).zfill(2)
       else:
          M = str(int(M))
-      YM = f"{Y}/{M}"
-      if YM not in destdirs: destdirs.append(YM)
-      fdict[f] = YM
+         D = str(int(D))
+
+      # eval is from https://stackoverflow.com/a/54071505/3569534
+      # use out subdirectory format based on what is provided by outsubdir string passed in to this function.
+      outsubdir = eval(f'f"""{subdirformat}"""')
+      if outsubdir not in destdirs: destdirs.append(outsubdir)
+      fdict[f] = outsubdir
    # finish the for f in flist
 
    # short-circuit if keyboard action happened in one of the nested functions
@@ -146,7 +227,7 @@ def make_YM_forest(outdir, flist, action = "symlink", dryrun=True, debuglevel=de
    for d in destdirs:
       dd = path.join(outdir,d)
       if debuglevel >= 3:
-         eprint(f"Make dir: {dd}")
+         print(f"mkdir {dd}")
       if not dryrun:
          Path(dd).mkdir(parents=True, exist_ok=True)
 
@@ -159,11 +240,11 @@ def make_YM_forest(outdir, flist, action = "symlink", dryrun=True, debuglevel=de
          ff = path.relpath(ff,destfile)
       if debuglevel >= 2:
          if action == "copy":
-            eprint(f"cp -p {ff} {destfile}")
+            print(f"cp -p {ff} {destfile}")
          elif action == "symlink":
-            eprint(f"ln -s {ff} {destfile}")
+            print(f"ln -s {ff} {destfile}")
          elif action == "move":
-            eprint(f"mv {ff} {destfile}")
+            print(f"mv {ff} {destfile}")
 
       if not dryrun:
       #if False: