Merge pull request #97 from CCBR/quite2quiet

chore: its quiet and not quite

CHANGELOG.md

@@ -4,6 +4,16 @@
 
 ### Bug fixes
 
+## spacesavers2 v0.12.1
+
+### New features
+
+- adding uid, human_readable_bytes and percent columns to `pdq` output 
+
+### Bug fixes
+
+- type fix "quite" to "quiet"
+
 ## spacesavers2 v0.12.0
 
 ### New features

spacesavers2_catalog

@@ -154,8 +154,8 @@ def main():
     )
     parser.add_argument(
         "-q",
-        "--quite",
-        dest="quite",
+        "--quiet",
+        dest="quiet",
         required=False,
         action=argparse.BooleanOptionalAction,
         help="Do not show progress",
@@ -184,7 +184,7 @@ def main():
     args = parser.parse_args()
 
     tqdm_disable = False
-    if args.quite: tqdm_disable = True
+    if args.quiet: tqdm_disable = True
 
     global sed
     sed = dict()

spacesavers2_e2e

@@ -59,7 +59,8 @@ spacesavers2_catalog \
     --outfile ${outfile_catalog} \
     --bottomhash \
     --brokenlink \
-    --geezers --quite
+    --geezers \
+    --quiet
 EOF
 )
 echo $cmd
@@ -138,4 +139,4 @@ fi
 done
 
 
-echo "Done!"
+echo "Done!"

spacesavers2_pdq

@@ -16,7 +16,7 @@ from multiprocessing import Pool
 import argparse
 from pathlib import Path
 import json
-import os
+import pandas as pd
 
 
 def task(f):
@@ -82,8 +82,8 @@ def main():
     )
     parser.add_argument(
         "-q",
-        "--quite",
-        dest="quite",
+        "--quiet",
+        dest="quiet",
         required=False,
         action=argparse.BooleanOptionalAction,
         help="Do not show progress",
@@ -98,7 +98,7 @@ def main():
     dirs = [p]
 
     tqdm_disable = False
-    if args.quite: tqdm_disable = True
+    if args.quiet: tqdm_disable = True
     # files = [p]
     # files2 = p.glob("**/*")
     # files.extend(files2)
@@ -127,6 +127,8 @@ def main():
 
     outdict=dict()
     outdict[str(p)]=dict()
+    col_names =  ['uid', 'username', 'ninodes', 'nbytes', 'human_readable']
+    df  = pd.DataFrame(columns = col_names)
 
     for uid in bigdict.keys():
         username = get_username_groupname(uid)
@@ -138,8 +140,27 @@ def main():
         outdict[str(p)][str(uid)]['username']=username
         outdict[str(p)][str(uid)]['ninodes']=ninodes
         outdict[str(p)][str(uid)]['nbytes']=nbytes
-        outfh.write(f"{username}\t{ninodes}\t{nbytes}\n")
-
+        my_dict = {'uid':uid,
+                   'username':username,
+                   'ninodes':ninodes,
+                   'nbytes':nbytes,
+                   'human_readable':get_human_readable_size(nbytes)}
+        df.loc[len(df)] = my_dict
+        # outfh.write(f"{username}\t{ninodes}\t{nbytes}\n")
+
+    total_ninodes = df['ninodes'].sum()    
+    total_nbytes = df['nbytes'].sum()
+    total_humanreadable = get_human_readable_size(total_nbytes)
+    my_dict = { 'uid':0,
+                'username':'allusers',
+                'ninodes':total_ninodes ,
+                'nbytes':total_nbytes,
+                'human_readable':total_humanreadable}
+    df.loc[len(df)] = my_dict
+    df.sort_values(by=['nbytes'],ascending=False,inplace=True)
+    df['percent'] = df['nbytes'] * 100.0 / total_nbytes
+    df['percent'] = df['percent'].apply(lambda x: float("{:.2f}".format(x)))
+    df.to_csv(outfh,sep="\t",index=False)    
     if args.json:
         json.dump(outdict,outjson,indent=1)
         outjson.close()

src/VERSION

@@ -1 +1 @@
-0.12.0
+0.12.1