# HG changeset patch
# User Igor Chubin <igor@chub.in>
# Date 1296211258 -7200
# Node ID d532e7b52ab22d45f691d22f344dd92cad9d6e96
# Parent  3ec83a7cc544d26e0ca43adcb2ed3c2a13eb1164
-s key support in new-words.py

Now new-words-py.sh -s works in the same way as new-words.sh.
(WPS and UWPS fields are not calculated correctly yet).

diff -r 3ec83a7cc544 -r d532e7b52ab2 new-words-py.sh
--- a/new-words-py.sh	Mon Jan 24 06:31:42 2011 +0100
+++ b/new-words-py.sh	Fri Jan 28 12:40:58 2011 +0200
@@ -283,7 +283,7 @@
    | part $PART_TO_PROCESS \
    | tee $ORIGINAL_TEXT \
    | two_and_three_words \
-   | get_words_group_words_add_stat \
+   | STAT_ONLY="$STAT_ONLY" get_words_group_words_add_stat \
    | tee "$TEMP1" > "$TEMP2"
 
 if [ "$STAT_ONLY" = "YES" ]
diff -r 3ec83a7cc544 -r d532e7b52ab2 new-words.py
--- a/new-words.py	Mon Jan 24 06:31:42 2011 +0100
+++ b/new-words.py	Fri Jan 28 12:40:58 2011 +0200
@@ -318,12 +318,32 @@
 
 def print_words_sorted(word_pairs, stats, print_stats=True, stats_only=False):
     if stats_only:
-        codecs.getwriter("utf-8")(sys.stdout).write("stat_only")
+        codecs.getwriter("utf-8")(sys.stdout).write(
+            " ".join([
+                "%-10s" % x for x in [
+                "LANG",
+                "KNOWN%",
+                "UNKNOWN%",
+                "KNOWN",
+                "TOTAL",
+                "WPS",
+                "UWPS*10"
+                ]]) + "\n")
+        codecs.getwriter("utf-8")(sys.stdout).write(
+            " ".join([
+                "%(language)-10s",
+                "%(percentage)-10.2f",
+                "%(percentage_unknown)-10.2f",
+                "%(total_known)-11d"
+                "%(total)-11d"
+                "%(wps)-11d"
+                "%(uwps)-11d"
+                ]) % stats + "\n")
         return
 
     if print_stats:
         codecs.getwriter("utf-8")(sys.stdout).write(
-            "# %(language)s, %(percentage)s, <%(total_known)s/%(total)s>, <%(groups)s/%(words)s>\n" % stats)
+            "# %(language)s, %(percentage)-7.2f, <%(total_known)s/%(total)s>, <%(groups)s/%(words)s>\n" % stats)
 
     level_lines = range(int(float(stats['percentage']))/5*5+5,95,5)+range(90,102)
     known = int(stats['total_known'])
@@ -360,6 +380,9 @@
     notes = load_notes(notes_filenames())
     lines = readlines_from_stdin()
     words = get_words(lines)
+    stats_only = False
+    if 'STAT_ONLY' in os.environ and os.environ['STAT_ONLY'] == 'YES':
+        stats_only = True
 
     stats = {}
     stats['total'] = sum(words[x] for x in words.keys())
@@ -367,10 +390,13 @@
 
     stats['total_unknown'] = sum(words[x] for x in words.keys())
     stats['total_known'] = stats['total'] - stats['total_unknown']
-    stats['percentage'] = "%7.2f"%(100.0*stats['total_known']/stats['total'])
+    stats['percentage'] = 100.0*stats['total_known']/stats['total']
+    stats['percentage_unknown'] = 100.0-100.0*stats['total_known']/stats['total']
     stats['groups'] = 0
     stats['words'] = len(words)
-    stats['sentences'] = 0 #FIXME
+    stats['sentences'] = 0  #FIXME
+    stats['wps'] = 0        #FIXME
+    stats['uwps'] = 0       #FIXME
     stats['language'] = config['language']
 
     linked_words = find_linked_words(notes)
@@ -386,7 +412,7 @@
                 cmp=lambda x,y:compare_word_pairs(x,y, wgw, normalizator, linked_words),
                 reverse=True)
 
-    print_words_sorted(word_pairs, stats)
+    print_words_sorted(word_pairs, stats, stats_only=stats_only)
 
 (options, args) = parser.parse_args()
 if options.language: