rda-python-miscs 1.0.1__tar.gz → 1.0.3__tar.gz

rda_python_miscs-1.0.3/MANIFEST.in

@@ -0,0 +1 @@
+include src/rda_python_miscs/*.usg

{rda_python_miscs-1.0.1/src/rda_python_miscs.egg-info → rda_python_miscs-1.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: rda_python_miscs
-Version: 1.0.1
+Version: 1.0.3
 Summary: RDA Python package to hold RDA miscellaneous utility programs
 Author-email: Zaihua Ji <zji@ucar.edu>
 Project-URL: Homepage, https://github.com/NCAR/rda-python-miscs
@@ -13,5 +13,6 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: rda_python_common
 Requires-Dist: rda_python_setuid
+Dynamic: license-file
 
 RDA python package to hold miscellaneous utility programs.

{rda_python_miscs-1.0.1 → rda_python_miscs-1.0.3}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rda_python_miscs"
-version = "1.0.1"
+version = "1.0.3"
 authors = [
   { name="Zaihua Ji", email="zji@ucar.edu" },
 ]
@@ -44,7 +44,9 @@ where = ["src"]
 "rdasub" = "rda_python_miscs.rdasub:main"
 "pgwget" = "rda_python_miscs.pgwget:main"
 "rdals" = "rda_python_miscs.rdals:main"
+"gdexls" = "rda_python_miscs.gdexls:main"
 "rdaps" = "rda_python_miscs.rdaps:main"
+"rdazip" = "rda_python_miscs.rdazip:main"
 "rdaown" = "rda_python_miscs.rdaown:main"
 "rdacp.py" = "rda_python_miscs.rdacp:main"
 "rdakill.py" = "rda_python_miscs.rdakill:main"

rda_python_miscs-1.0.3/src/rda_python_miscs/gdexls.py

@@ -0,0 +1,279 @@
+#!/usr/bin/env python3
+#
+##################################################################################
+#
+#     Title: gdexls
+#    Author: Zaihua Ji, zji@ucar.edu
+#      Date: 10/20/2020
+#            2025-03-10 transferred to package rda_python_miscs from
+#            https://github.com/NCAR/rda-utility-programs.git
+#            2025-09-21 copied from rdals to gdexls
+#   Purpose: list files/directories in a local directory and show additional
+#            information recorded in RDADB if any
+#
+#    Github: https://github.com/NCAR/rda-python-miscs.git
+#
+##################################################################################
+#
+import re
+import os
+import sys
+import glob
+from os import path as op
+from rda_python_common import PgLOG
+from rda_python_common import PgDBI
+from rda_python_common import PgUtil
+from rda_python_common import PgSplit
+
+# define some constants for gdexls actions
+DIDX = 3   # description column index
+CLMT = 500   # reformat list if count reach this limit
+WIDTHS = [0, 0, 0]   # WIDTHS for formated display
+ALIGNS = [0, 1, 1]   # alignment, 0 - left; 1 - right
+
+RDALS = {
+   'd' : 0,     # 1 to list directory information only
+   'f' : 0,     # 1 to list file information only
+   'N' : 0,     # 1 to list files unformatted
+   'r' : 0,     # 1 if recursive all
+   'R' : 0,     # > 0 to set recursive limit
+   'D' : None,  # specify delimiting symbols, default to '  '
+}
+
+LINFO = {
+   'files' : [],
+   'curdir' : None,
+   'tpath' : None,
+   'dhome' : None,
+   'dsid' : None,
+   'dcnt' : 0,
+   'gcnt' : 0,
+   'fcnt' : 0,
+   'pcnt' : 0,
+   'pgrecs' : []
+}
+
+#
+# main function to run the application
+#
+def main():
+
+   PgDBI.view_dbinfo()
+   PgLOG.set_help_path(__file__)
+   PgLOG.PGLOG['LOGFILE'] = "gdexls.log"   # set different log file
+   LINFO['curdir'] = get_real_path(os.getcwd())
+   argv = sys.argv[1:]
+   PgLOG.pglog("gdexls {} ({})".format(' '.join(argv), LINFO['curdir']))
+   option = defopt = 'l'
+   for arg in argv:
+      if re.match(r'-(h|-*help|\?)$', arg): PgLOG.show_usage("gdexls")
+      ms = re.match(r'-(\w)$', arg)
+      if ms:
+         option = ms.group(1)
+         if option not in RDALS: PgLOG.pglog(arg + ": Unknown Option", PgLOG.LGEREX)
+         if 'dfNr'.find(option) > -1:
+            RDALS[option] = 1
+            option = defopt
+         continue
+      if not option: PgLOG.pglog(arg + ": Value provided without option", PgLOG.LGEREX)
+      if option == 'l':
+         LINFO['files'].append(get_real_path(arg))
+         defopt = None
+      else:
+         if option == 'R':
+            RDALS[option] = int(arg)
+         else:
+            RDALS[option] = arg
+         option = defopt
+   
+   if not LINFO['files']:
+      LINFO['files'] = sorted(glob.glob('*'))   # view all files in current directory
+      if not LINFO['files']:
+         sys.stderr.write(LINFO['curdir'] + ": Empty directory\n")
+         PgLOG.pgexit(1)
+
+   if not (RDALS['d'] or RDALS['f']):
+      RDALS['d'] = RDALS['f'] = 1   # list both directories and files as default
+   if not RDALS['D']: RDALS['D'] = '|' if RDALS['N'] else "  "    # default delimiter for no format display
+   if not RDALS['R'] and RDALS['r']: RDALS['R'] = 1000
+
+   display_top_list(LINFO['files'])   # display or cache file/directory list
+   if LINFO['pcnt'] > 0: display_format_list()   # if some left over
+
+   if (LINFO['dcnt'] + LINFO['gcnt'] + LINFO['fcnt']) > 1:
+      msg = ''
+      if LINFO['dcnt'] > 0:
+         s = 's' if LINFO['dcnt'] > 1 else ''
+         msg += "{} Dataset{}".format(LINFO['dcnt'], s)
+      if LINFO['gcnt'] > 0:
+         s = 's' if LINFO['gcnt'] > 1 else ''
+         if msg: msg += " & "
+         msg += "{} Group{}".format(LINFO['gcnt'], s)
+      if LINFO['fcnt'] > 0:
+         s = 's' if LINFO['fcnt'] > 1 else ''
+         if msg: msg += " & "
+         msg += "{} File{}".format(LINFO['fcnt'], s)
+      print("Total {} displayed".format(msg))
+   elif (LINFO['dcnt'] + LINFO['gcnt'] + LINFO['fcnt']) == 0:
+      sys.stderr.write((LINFO['tpath'] if LINFO['tpath'] else LINFO['curdir']) + ": No RDA data information found\n")
+      PgLOG.pgexit(1)
+   
+   PgLOG.pgexit(0)
+
+#
+# display the top level list
+#
+def display_top_list(files):
+
+   for file in files:
+
+      if not op.exists(file):
+         sys.stderr.write(file + ": NOT exists\n")
+         continue
+
+      isdir = 1 if op.isdir(file) else 0
+      display = 1
+      if isdir and re.search(r'/$', file):
+         display = 0   # do not display the directory info if it is ended by '/'
+         file = re.sub(r'/$', '', file)
+
+      if not re.match(r'^/', file): file = PgLOG.join_paths(LINFO['curdir'], file)
+      LINFO['tpath'] = (op.dirname(file) if display else file) + "/"
+      if display: display_line(file, isdir)
+      if isdir and (RDALS['R'] or not display or not LINFO['dsid']):
+         fs = sorted(glob.glob(file + "/*"))
+         display_list(fs, 1)
+         if LINFO['pcnt'] > CLMT: display_format_list()
+
+#
+# recursively display directory/file info
+#
+def display_list(files, level):
+
+   for file in files:
+      isdir = 1 if op.isdir(file) else 0
+      display_line(file, isdir)
+      if isdir and level < RDALS['R']:
+         fs = sorted(glob.glob(file + "/*"))
+         display_list(fs, level+1)
+         if LINFO['pcnt'] > CLMT: display_format_list()
+
+#
+# find dataset/group info; display or cache file
+#
+def display_line(file, isdir):
+   
+   getwfile = 1
+   if LINFO['dsid'] and LINFO['dhome']:
+      ms = re.match(r'^{}/(.*)$'.format(LINFO['dhome']), file)
+      if ms:
+         wfile = ms.group(1)
+         getwfile = 0
+   if getwfile:
+      LINFO['dsid'] = PgUtil.find_dataset_id(file, logact = PgLOG.LOGWRN)
+      if LINFO['dsid'] == None: return     # skip for missing dsid
+
+      pgrec = PgDBI.pgget("dataset", "title, (dwebcnt + nwebcnt) nc, (dweb_size + nweb_size) ns", "dsid = '{}'".format(LINFO['dsid']), PgLOG.LGEREX)
+      if not pgrec: return None
+
+      LINFO['dhome'] = "{}/{}".format(PgLOG.PGLOG['DSDHOME'], LINFO['dsid'])
+      if LINFO['dhome'] == file:
+         file = re.sub(r'^{}'.format(LINFO['tpath']), '', file, 1)
+         if RDALS['d']:
+            title = pgrec['title'] if pgrec['title'] else ''
+            display_record(["D" + file, pgrec['ns'], str(pgrec['nc']), title])
+         LINFO['dcnt'] += 1
+         return
+
+      ms = re.match(r'^{}/(.*)$'.format(LINFO['dhome']), file)
+      if ms:
+         wfile = ms.group(1)
+      else:
+         return
+
+   if isdir:
+      if RDALS['d']:   # check and display group info for directory
+         pgrec = PgDBI.pgget("dsgroup", "title, (dwebcnt + nwebcnt) nc, (dweb_size + nweb_size) ns",
+                             "dsid = '{}' AND webpath = '{}'".format(LINFO['dsid'], wfile), PgLOG.LGEREX)
+         if pgrec:
+            file = re.sub(r'^{}'.format(LINFO['tpath']), '', file, 1)
+            title = pgrec['title'] if pgrec['title'] else ''
+            display_record(["G" + file, pgrec['ns'], str(pgrec['nc']), title])
+            LINFO['gcnt'] += 1
+
+   elif RDALS['f']:   # check and display file info
+      pgrec = PgSplit.pgget_wfile(LINFO['dsid'], "data_size, data_format, note",
+                          "wfile = '{}'".format(wfile), PgLOG.LGEREX)
+      if pgrec:
+         if pgrec['note']:
+            note = re.sub(r'\n', ' ', pgrec['note'])   # remove '\n' in note
+         else:
+            note = ''
+         file = re.sub(r'^{}'.format(LINFO['tpath']), '', file, 1)
+         display_record(["F" + file, pgrec['data_size'], pgrec['data_format'], note])
+         LINFO['fcnt'] += 1
+
+#
+# display one file info
+#
+def display_record(disp):
+
+   disp[1] = get_float_string(disp[1])
+   if RDALS['N']:
+      print(RDALS['D'].join(disp))
+   else:
+      LINFO['pgrecs'].append(disp)
+      LINFO['pcnt'] += 1
+      for i in range(DIDX):
+         dlen = len(disp[i])
+         if dlen > WIDTHS[i]: WIDTHS[i] = dlen
+
+#
+# display cached list with format
+#
+def display_format_list():
+
+   for j in range(LINFO['pcnt']):
+      disp = LINFO['pgrecs'][j]
+      for i in range(DIDX):
+         if ALIGNS[i] == 1:
+            disp[i] = "{:>{}}".format(disp[i], WIDTHS[i])
+         else:
+            disp[i] = "{:{}}".format(disp[i], WIDTHS[i])
+      print(RDALS['D'].join(disp))
+
+   LINFO['pcnt'] = 0
+
+#
+# change size to floating point value with unit
+#
+def get_float_string(val):
+
+   units = ['B', 'K', 'M', 'G', 'T', 'P']
+
+   idx = 0
+   while val > 1000 and idx < 5:
+      val /= 1000
+      idx += 1
+
+   if idx > 0:
+      return "{:.2f}{}".format(val, units[idx])
+   else:
+      return "{}{}".format(val, units[idx])
+
+#
+# replace /gpfs to the path /glade
+#
+def get_real_path(path):
+
+   if re.match(r'^/gpfs/u', path):
+      path = re.sub(r'^/gpfs', '/glade', path, 1)
+   elif re.match(r'^/gpfs/csfs1/', path):
+      path = re.sub(r'^/gpfs/csfs1', '/glade/campaign', path, 1)
+
+   return path
+
+#
+# call main() to start program
+#
+if __name__ == "__main__": main()

rda_python_miscs-1.0.3/src/rda_python_miscs/gdexls.usg

@@ -0,0 +1,60 @@
+
+ List directory and file information of the current or specified directories
+ with metadata information if matched. Four columns are listed, they are Directory
+ Name, Data Volume, File Count, and Brief Description if the listed item is a
+ directory, and they are File Name, Data Size, Data Format, and Brief Description
+ if the listed item is a file.
+ 
+ A leading letter is displayed on each line to indicate what type item is listed;
+ including 'D' for a whole dataset, 'G' for a group or subgroup in a dataset,
+ and 'F' for a data file.
+ 
+ The output of directory/file list is formatted as default with double spaces
+ as delimiter and each column lined up vertically at least for the files under each
+ directory. Provide Option -N to display list without format. A delimiter symbol '|'
+ is defaulted if Option -N is present.
+ 
+ Usage: gdexls [-d] [-f] [-N] [-h] [-r] [-D DelimitSymbols] [-R RecursiveLevel] [Directory/File List]
+
+      - Option -d, list directory information only. Directory information
+        is included as default. Add this option to exclude file information;
+ 
+      - Option -f, list file information only. File information
+        is included as default. Add this option to exclude directory information;
+ 
+      - Option -N, list files unformatted;
+
+      - Option -h, display this help document;
+
+      - Option -r, list directories and files recursively;
+
+      - Option -R, list directories and files recursively up to the level 
+        provided with this Option;
+
+      - Option -D, specify delimiting symbols for dividing the columns.
+        It defaults to "  " for formatted output and '|' for unformatted output.
+        Make sure quote the symbols if any character in the symbols has Unix
+        meaning, for example -D '<:>';
+
+      - Directory/file List is optional; without specification, all directories
+        and files in the current directory are listed. Unix command line
+        wildcards are supported.
+
+  This utility program can be executed anywhere. Nothing is displayed if neither
+  directory nor file information pre-gathered in database.
+  
+  For examples, to check directories and files of ds277.6, you can
+     
+     1. Change into the dataset home data directory as 'cd /PathTo/ds277.6' and
+        execute 'gdexls'; add recursive option '-r' to check directories and files
+        further into the sub-directories, or change directory into a sub-directory
+        to check files inside of it.
+     
+     2. Pass an absolute path to gdexls as 'gdexls /PathTo/ds277.6/' or as
+        'gdexls /PathTo/ds277.6/*'; without the ending by '/' or an appended
+        wildcard symbol '*' information of the dataset itself is check unless
+        the recursive option '-r' or '-R RecursiveLevel' is present
+     
+     3. If the current directory is in another dataset home data directory,
+        such as /PathTo/ds277.7, you can pass a relative path to gdexls
+        as  'gdexls ../ds277.6/' or as 'gdexls ../ds277.6/*'

{rda_python_miscs-1.0.1 → rda_python_miscs-1.0.3/src/rda_python_miscs.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: rda_python_miscs
-Version: 1.0.1
+Version: 1.0.3
 Summary: RDA Python package to hold RDA miscellaneous utility programs
 Author-email: Zaihua Ji <zji@ucar.edu>
 Project-URL: Homepage, https://github.com/NCAR/rda-python-miscs
@@ -13,5 +13,6 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: rda_python_common
 Requires-Dist: rda_python_setuid
+Dynamic: license-file
 
 RDA python package to hold miscellaneous utility programs.

{rda_python_miscs-1.0.1 → rda_python_miscs-1.0.3}/src/rda_python_miscs.egg-info/SOURCES.txt

@@ -5,6 +5,8 @@ pyproject.toml
 src/rda_python_miscs/__init__.py
 src/rda_python_miscs/bashqsub.py
 src/rda_python_miscs/bashqsub.usg
+src/rda_python_miscs/gdexls.py
+src/rda_python_miscs/gdexls.usg
 src/rda_python_miscs/pgwget.py
 src/rda_python_miscs/rdacp.py
 src/rda_python_miscs/rdacp.usg

{rda_python_miscs-1.0.1 → rda_python_miscs-1.0.3}/src/rda_python_miscs.egg-info/entry_points.txt

@@ -1,5 +1,6 @@
 [console_scripts]
 bashqsub = rda_python_miscs.bashqsub:main
+gdexls = rda_python_miscs.gdexls:main
 pgwget = rda_python_miscs.pgwget:main
 rdacp.py = rda_python_miscs.rdacp:main
 rdakill.py = rda_python_miscs.rdakill:main
@@ -8,4 +9,5 @@ rdamod.py = rda_python_miscs.rdamod:main
 rdaown = rda_python_miscs.rdaown:main
 rdaps = rda_python_miscs.rdaps:main
 rdasub = rda_python_miscs.rdasub:main
+rdazip = rda_python_miscs.rdazip:main
 tcshqsub = rda_python_miscs.tcshqsub:main

rda_python_miscs-1.0.1/MANIFEST.in

@@ -1,10 +0,0 @@
-include src/rda_python_miscs/bashqsub.usg
-include src/rda_python_miscs/tcshqsub.usg
-include src/rda_python_miscs/rdasub.usg
-include src/rda_python_miscs/rdacp.usg
-include src/rda_python_miscs/rdakill.usg
-include src/rda_python_miscs/rdals.usg
-include src/rda_python_miscs/rdamod.usg
-include src/rda_python_miscs/rdaown.usg
-include src/rda_python_miscs/rdaps.usg
-include src/rda_python_miscs/rdazip.usg