handlers: remove remnant bits of python2 compat

src/filters/cmdtalk.py

@@ -20,8 +20,6 @@
 # All data is binary. This is important for Python3
 # All parameter names are converted to and processed as str/unicode
 
-from __future__ import print_function
-
 import sys
 import os
 import tempfile

src/filters/rclbasehandler.py

@@ -18,8 +18,6 @@
 # Base for extractor classes. With some common generic implementations
 # for the boilerplate functions.
 
-from __future__ import print_function
-
 import os
 import sys
 import rclexecm

src/filters/rcldia.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-from __future__ import print_function
 
 # dia (http://live.gnome.org/Dia) file filter for recoll
 # stefan.friedel@iwr.uni-heidelberg.de 2012

src/filters/rcldjvu.py

@@ -17,8 +17,6 @@
 
 # Recoll DJVU extractor
 
-from __future__ import print_function
-
 import os
 import sys
 import re

src/filters/rcldoc.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-from __future__ import print_function
 
 import rclexecm
 import rclexec1

src/filters/rclepub.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 """Extract Html content from an EPUB file (.epub)"""
-from __future__ import print_function
 
 rclepub_html_mtype = "text/html"
 

src/filters/rclepub1.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 """Extract Html content from an EPUB file (.chm), concatenating all sections"""
-from __future__ import print_function
 
 import sys
 import os

src/filters/rclexec1.py

@@ -26,8 +26,6 @@
 # this would be to slow. So this helps implementing a permanent script
 # to repeatedly execute single commands.
 
-from __future__ import print_function
-
 import subprocess
 import rclexecm
 from rclbasehandler import RclBaseHandler

src/filters/rclexecm.py

@@ -20,8 +20,6 @@
 # All data is binary. This is important for Python3
 # All parameter names are converted to and processed as str/unicode
 
-from __future__ import print_function
-
 import sys
 import os
 import tempfile
@@ -30,7 +28,6 @@ import getopt
 import rclconfig
 import cmdtalk
 
-PY3 = (sys.version > '3')
 _g_mswindows = (sys.platform == "win32")
 _g_execdir = os.path.dirname(sys.argv[0])
 
@@ -62,12 +59,11 @@ def makebytes(data):
 # Possibly decode binary file name for use as subprocess argument,
 # depending on platform.
 def subprocfile(fn):
-    # On Windows PY3 the list2cmdline() method in subprocess assumes that
+    # On Windows Python 3 the list2cmdline() method in subprocess assumes that all args are str, and
-    # all args are str, and we receive file names as UTF-8. So we need
+    # we receive file names as UTF-8. So we need to convert.
-    # to convert.
+    # On Unix all list elements get converted to bytes in the C _posixsubprocess module, nothing to
-    # On Unix all list elements get converted to bytes in the C
+    # do.
-    # _posixsubprocess module, nothing to do.
+    if _g_mswindows and type(fn) != type(''):
-    if PY3 and _g_mswindows and type(fn) != type(''):
         return fn.decode('UTF-8')
     else:
         return fn
@@ -383,10 +379,7 @@ def main(proto, extract):
         print("Open error", file=sys.stderr)
         sys.exit(1)
 
-    if PY3:
+    ioout = sys.stdout.buffer
-        ioout = sys.stdout.buffer
-    else:
-        ioout = sys.stdout
     if ipath != b"" or actAsSingle:
         params['ipath'] = ipath
         ok, data, ipath, eof = extract.getipath(params)

src/filters/rclfb2.py

@@ -16,8 +16,6 @@
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 ######################################
 
-from __future__ import print_function
-
 import sys
 import rclexecm
 import rclxslt

src/filters/rclgenxslt.py

@@ -18,8 +18,6 @@
 
 # Base class for simple (one stylesheet) xslt-based handlers
 
-from __future__ import print_function
-
 import sys
 import rclxslt
 import gzip

src/filters/rclics.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-from __future__ import print_function
 
 # Read an ICS file, break it into "documents" which are events, todos,
 # or journal entries, and interface with recoll execm

src/filters/rclimg.py

@@ -6,7 +6,6 @@
 #
 # Uses pyexiv2. Also tried Pillow, found it useless for tags.
 #
-from __future__ import print_function
 
 import sys
 import os

src/filters/rclinfo.py

@@ -3,8 +3,6 @@
 # Read a file in GNU info format and output its nodes as subdocs,
 # interfacing with recoll execm
 
-from __future__ import print_function
-
 import rclexecm
 import sys
 import os

src/filters/rclipynb.py

@@ -17,8 +17,6 @@
 
 # Recoll handler for iPython / Jupyter notebook files.
 
-from __future__ import print_function
-
 import os
 import sys
 import json

src/filters/rclkar.py

@@ -1,8 +1,6 @@
 #!/usr/bin/env python3
 
 # Read a .kar midi karaoke file and translate to recoll indexable format
-# This does not work with Python3 yet because python:midi doesn't 
-from __future__ import print_function
 
 import rclexecm
 import sys
@@ -46,11 +44,7 @@ htmltemplate = '''
 
 nlbytes = b'\n'
 bsbytes = b'\\'
-PY3 = sys.version > '3'
+nullchar = 0
-if PY3:
-    nullchar = 0
-else:
-    nullchar = chr(0)
     
 class KarTextExtractor(RclBaseHandler):
     # Afaik, the only charset encodings with null bytes are variations on

src/filters/rcllatinclass.py

@@ -13,12 +13,7 @@ epsilon with dasia (in unicode but not iso). Can this be replaced by either epsi
 with acute accent ?
 """
 
-from __future__ import print_function
-
 import sys
-PY3 = sys.version > '3'
-if not PY3:
-    import string
 import glob
 import os
 import os.path
@@ -38,10 +33,7 @@ class European8859TextClassifier:
         # Table to translate from punctuation to spaces
         self.punct = b'''0123456789<>/*?[].@+-,#_$%&={};.,:!"''' + b"'\n\r"
         spaces = len(self.punct) * b' '
-        if PY3:
+        self.spacetable = bytes.maketrans(self.punct, spaces)
-            self.spacetable = bytes.maketrans(self.punct, spaces)
-        else:
-            self.spacetable = string.maketrans(self.punct, spaces)
 
     def readlanguages(self, langzip):
         """Extract the stop words lists from the zip file.

src/filters/rclmidi.py

@@ -23,24 +23,15 @@
 # CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 # 
-from __future__ import print_function
 
 import sys
 from struct import unpack, pack
 import six
 
-PY3 = sys.version > '3'
+def next_byte_as_int(data):
-
+    return next(data)
-if PY3:
+def next_byte_as_char(data):
-    def next_byte_as_int(data):
+    return bytes([next(data)])
-        return next(data)
-    def next_byte_as_char(data):
-        return bytes([next(data)])
-else:
-    def next_byte_as_int(data):
-        return ord(data.next())
-    def next_byte_as_char(data):
-        return next(data)
 
 ##
 ## Constants
@@ -270,12 +261,8 @@ class NoteEvent(Event):
                                 self.velocity)
 
     def decode_data(self):
-        if PY3:
+        self.pitch = self.data[0]
-            self.pitch = self.data[0]
+        self.velocity = self.data[1]
-            self.velocity = self.data[1]
-        else:
-            self.pitch = ord(self.data[0])
-            self.velocity = ord(self.data[1])
 
 
 class NoteOnEvent(NoteEvent):
@@ -309,12 +296,8 @@ class ControlChangeEvent(Event):
                                 hex(ord(self.data[1])))
 
     def decode_data(self):
-        if PY3:
+        self.control = self.data[0]
-            self.control = self.data[0]
+        self.value = self.data[1]
-            self.value = self.data[1]
-        else:
-            self.control = ord(self.data[0])
-            self.value = ord(self.data[1])
 
 
 class ProgramChangeEvent(Event):
@@ -328,10 +311,7 @@ class ProgramChangeEvent(Event):
                                 hex(ord(self.data[0])))
 
     def decode_data(self):
-        if PY3:
+        self.value = self.data[0]
-            self.value = self.data[0]
-        else:
-            self.value = ord(self.data[0])
 
 
 class ChannelAfterTouchEvent(Event):
@@ -356,12 +336,8 @@ class PitchWheelEvent(Event):
                                 hex(ord(self.data[1])))
 
     def decode_data(self):
-        if PY3:
+        first = self.data[0]
-            first = self.data[0]
+        second = self.data[1]
-            second = self.data[1]
-        else:
-            first = ord(self.data[0]) 
-            second = ord(self.data[1])
         self.value = ((second << 7) | first) - 0x2000
 
 
@@ -461,10 +437,7 @@ class PortEvent(MetaEvent):
 
     def decode_data(self):
         assert(len(self.data) == 1)
-        if PY3:
+        self.port = self.data[0]
-            self.port = self.data[0]
-        else:
-            self.port = ord(self.data[0])
 
 class TrackLoopEvent(MetaEvent):
     name = 'Track Loop'
@@ -498,13 +471,7 @@ class SetTempoEvent(MetaEvent):
 
     def decode_data(self):
         assert(len(self.data) == 3)
-        if PY3:
+        self.mpqn = (self.data[0] << 16) + (self.data[1] << 8) + self.data[2]
-            self.mpqn = (self.data[0] << 16) + (self.data[1] << 8) \
-                        + self.data[2]
-        else:
-            self.mpqn = (ord(self.data[0]) << 16) + (ord(self.data[1]) << 8) \
-                        + ord(self.data[2])
-
         self.tempo = float(6e7) / self.mpqn
 
 
@@ -523,22 +490,13 @@ class TimeSignatureEvent(MetaEvent):
                             (super(TimeSignatureEvent, self).__str__(),
                                 self.numerator, self.denominator,
                                 self.metronome, self.thirtyseconds)
-    if PY3:
+    def decode_data(self):
-        def decode_data(self):
+        assert(len(self.data) == 4)
-            assert(len(self.data) == 4)
+        self.numerator = self.data[0]
-            self.numerator = self.data[0]
+        # Weird: the denominator is two to the power of the data variable
-            # Weird: the denominator is two to the power of the data variable
+        self.denominator = 2 ** self.data[1]
-            self.denominator = 2 ** self.data[1]
+        self.metronome = self.data[2]
-            self.metronome = self.data[2]
+        self.thirtyseconds = self.data[3]
-            self.thirtyseconds = self.data[3]
-    else:
-        def decode_data(self):
-            assert(len(self.data) == 4)
-            self.numerator = ord(self.data[0])
-            # Weird: the denominator is two to the power of the data variable
-            self.denominator = 2 ** ord(self.data[1])
-            self.metronome = ord(self.data[2])
-            self.thirtyseconds = ord(self.data[3])
 
 
 class KeySignatureEvent(MetaEvent):

src/filters/rclppt.py

@@ -2,8 +2,6 @@
 
 # Recoll PPT text extractor
 
-from __future__ import print_function
-
 import rclexecm
 import rclexec1
 import re

src/filters/rclrar.py

@@ -18,8 +18,6 @@
 #   Free Software Foundation, Inc.,
 #   51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
-from __future__ import print_function
-
 import sys
 import rclexecm
 import os

src/filters/rclrtf.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-from __future__ import print_function
 
 import rclexecm
 import rclexec1

src/filters/rcltar.py

@@ -6,8 +6,6 @@
 # It works not only for tar-files, but automatically for gzipped and
 # bzipped tar-files at well.
 
-from __future__ import print_function
-
 import rclexecm
 
 try:

src/filters/rcltext.py

@@ -18,8 +18,6 @@
 # Wrapping a text file. Recoll does it internally in most cases, but
 # this is for use by another filter.
 
-from __future__ import print_function
-
 import rclexecm
 import sys
 from rclbasehandler import RclBaseHandler

src/filters/rcltxtlines.py

@@ -2,7 +2,6 @@
 """Index text lines as document (execm handler sample). This exists
 to demonstrate the execm interface and is not meant to be useful or
 efficient"""
-from __future__ import print_function
 
 import sys
 import os

src/filters/rcluncomp.py

@@ -1,5 +1,4 @@
 # No shebang: this is only used on Windows. We use a shell script on Linux
-from __future__ import print_function
 
 import rclexecm
 import sys

src/filters/rclwar.py

@@ -2,8 +2,6 @@
 
 # WAR web archive filter for recoll. War file are gzipped tar files
 
-from __future__ import print_function
-
 import rclexecm
 import tarfile
 

src/filters/rclxmp.py

@@ -16,7 +16,6 @@
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
 # Code to extract XMP tags using libexempi and python-xmp
-from __future__ import print_function
 
 can_xmp = True
 try:

src/filters/rclzip.py

@@ -18,8 +18,6 @@
 
 # Zip file extractor for Recoll
 
-from __future__ import print_function
-
 import os
 import posixpath
 import fnmatch
@@ -155,14 +153,11 @@ class ZipExtractor:
             if skipped is not None:
                 self.skiplist += conftree.stringToStrings(skipped)
         try:
-            if rclexecm.PY3:
+            # Note: py3 ZipFile wants an str file name, which
-                # Note: py3 ZipFile wants an str file name, which
+            # is wrong: file names are binary. But it accepts an
-                # is wrong: file names are binary. But it accepts an
+            # open file, and open() has no such restriction
-                # open file, and open() has no such restriction
+            self.f = open(filename, 'rb')
-                self.f = open(filename, 'rb')
+            self.zip = ZipFile(self.f)
-                self.zip = ZipFile(self.f)
-            else:
-                self.zip = ZipFile(filename)
             return True
         except Exception as err:
             self.em.rclog("openfile: failed: [%s]" % err)

src/filters/xlsxmltocsv.py

@@ -23,8 +23,6 @@
 # the minimum version supported.
 
 
-from __future__ import print_function
-
 import sys
 import xml.sax