rclzip: add useSkippedNames variable to also use the base skippedNames

src/filters/rclzip

@@ -28,6 +28,7 @@ from zipfile import ZipFile
 
 try:
     from recoll import rclconfig
+    from recoll import conftree
     hasrclconfig = True
 except:
     hasrclconfig = False
@@ -118,10 +119,14 @@ class ZipExtractor:
         if hasrclconfig:
             config = rclconfig.RclConfig()
             config.setKeyDir(os.path.dirname(filename))
+            usebaseskipped = config.getConfParam("zipUseSkippedNames")
+            if usebaseskipped:
+                skipped = config.getConfParam("skippedNames")
+                self.em.rclog("skippedNames: %s"%self.skiplist)
+                self.skiplist += conftree.stringToStrings(skipped)
             skipped = config.getConfParam("zipSkippedNames")
             if skipped is not None:
-                self.skiplist = skipped.split(" ")
+                self.skiplist += conftree.stringToStrings(skipped)
-
         try:
             if rclexecm.PY3:
                 # Note: py3 ZipFile wants an str file name, which

src/python/recoll/recoll/conftree.py

@@ -251,3 +251,21 @@ class ConfStack(object):
         if v and dodecode:
             v = v.decode('utf-8')
         return v
+
+def stringToStrings(s):
+    '''Parse a string made of space-separated words and C-Style strings
+    (double-quoted with backslash escape). E.g.:
+        word1 word2 "compound \\"quoted\\" string" ->
+        ['word1', 'word2', 'compound "quoted string']'''
+    import shlex
+    lex = shlex.shlex(s, posix=True)
+    lex.quotes = '"'
+    lex.escape = '\\'
+    lex.escapedquotes = '"'
+    l = []
+    while True:
+        tok = lex.get_token()
+        if not tok:
+            break
+        l.append(tok)
+    return l

src/sampleconf/recoll.conf

@@ -120,14 +120,24 @@ skippedPaths = /media
 #daemSkippedPaths = 
 
 
+# <var name="zipUseSkippedNames" type="bool">
+#
+# <brief>Use skippedNames inside Zip archives.</brief><descr>Fetched
+# directly by the rclzip handler. Skip the patterns defined by skippedNames
+# inside Zip archives. Can be redefined for subdirectories. 
+# See https://www.lesbonscomptes.com/recoll/faqsandhowtos/FilteringOutZipArchiveMembers.html
+# </descr></var>
+#zipUseSkippedNames =
+
 # <var name="zipSkippedNames" type="string">
 #
 # <brief>Space-separated list of wildcard expressions for names that should
 # be ignored inside zip archives.</brief><descr>This is used directly by
-# the zip handler, and has a function similar to skippedNames, but works
+# the zip handler. If zipUseSkippedNames is not set, zipSkippedNames
-# independantly. Can be redefined for subdirectories. Supported by recoll
+# defines the patterns to be skipped inside archives. If zipUseSkippedNames
-# 1.20 and newer. See
+# is set, the two lists are concatenated and used. Can be redefined for
-# https://www.lesbonscomptes.com/recoll/faqsandhowtos/FilteringOutZipArchiveMembers.html
+# subdirectories. 
+# See https://www.lesbonscomptes.com/recoll/faqsandhowtos/FilteringOutZipArchiveMembers.html
 # </descr></var>
 #zipSkippedNames =