Fix Python 3 correctness bugs found in code review

Fix str/bytes and leftover-py2 defects across the plugin, several on live
decryption paths:

  - erdr2pml.py: getText() footnote/sidebar handling mixed a bytes
    accumulator with str literals and called ord() on a bytes element,
    crashing on eReader/.pdb books that contain footnotes or sidebars.
  - ion.py: readdecimal() did `[ord(x) for x in self.read(...)]` over
    bytes (ord(int)), crashing KFX decryption on Ion DECIMAL values;
    printlob() had the same ord()-over-bytes in its debug path.
  - zipfilerugged.py: `isinstance(file, unicode)` raised NameError when a
    file-like object (not a path string) was passed to the ZipFile.
  - utilities.py: SafeUnbuffered.write referenced the undefined `unicode`
    (same fix already applied to the obok copy).
  - ineptpdf.py: ord(bookkey[0]) over an int in an error-diagnostic print.
  - epubfontdecrypt.py: removed a dead py2 itertools.izip fallback.
  - convert2xml.py: escapestr did bytes.replace(str, ...).
  - kgenpids.py: decode() built a str result then += bytes.

Cleanups from the earlier shim removal: drop now-unused `import sys`
(alfcrypto, utilities, kgenpids); unicode_argv returns list(sys.argv) so
callers can't mutate the process-global sys.argv.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

DeDRM_plugin/alfcrypto.py

@@ -8,7 +8,6 @@
 # pbkdf2.py Copyright © 2009 Daniel Holth <dholth@fastmail.fm>
 # pbkdf2.py This code may be freely used and modified for any purpose.
 
-import sys
 import hmac
 from struct import pack
 import hashlib

DeDRM_plugin/argv_utils.py

@@ -8,7 +8,7 @@ def unicode_argv(default_name):
     # On Python 3 sys.argv is already a list of Unicode strings on every
     # platform, so no special handling is needed.
     if len(sys.argv) > 0:
-        return sys.argv
+        return list(sys.argv)
     # if we don't have any arguments at all, just pass back the script name
     # this should never happen
     return [default_name]

DeDRM_plugin/convert2xml.py

@@ -124,10 +124,10 @@ class Dictionary(object):
         self.pos = 0
 
     def escapestr(self, str):
-        str = str.replace('&','&')
-        str = str.replace('<','&lt;')
-        str = str.replace('>','&gt;')
-        str = str.replace('=','&#61;')
+        str = str.replace(b'&',b'&amp;')
+        str = str.replace(b'<',b'&lt;')
+        str = str.replace(b'>',b'&gt;')
+        str = str.replace(b'=',b'&#61;')
         return str
 
     def lookup(self,val):

DeDRM_plugin/epubfontdecrypt.py

@@ -134,12 +134,7 @@ class Decryptor(object):
             return data
 
     def deobfuscate_single_data(self, key, data):
-        try: 
-            msg = bytes([c^k for c,k in zip(data, itertools.cycle(key))])
-        except TypeError:
-            # Python 2
-            msg = ''.join(chr(ord(c)^ord(k)) for c,k in itertools.izip(data, itertools.cycle(key)))
-        return msg
+        return bytes([c^k for c,k in zip(data, itertools.cycle(key))])
 
 
 

DeDRM_plugin/erdr2pml.py

@@ -314,7 +314,7 @@ class EreaderProcessor(object):
 
         # now handle footnotes pages
         if self.num_footnote_pages > 0:
-            r += '\n'
+            r += b'\n'
             # the record 0 of the footnote section must pass through the Xor Table to make it useful
             sect = self.section_reader(self.first_footnote_page)
             fnote_ids = deXOR(sect, 0, self.xortable)
@@ -322,11 +322,11 @@ class EreaderProcessor(object):
             des = DES.new(fixKey(self.content_key), DES.MODE_ECB)
             for i in range(1,self.num_footnote_pages):
                 logging.debug('get footnotepage %d', i)
-                id_len = ord(fnote_ids[2])
+                id_len = fnote_ids[2]
                 id = fnote_ids[3:3+id_len]
-                fmarker = '<footnote id="%s">\n' % id
+                fmarker = b'<footnote id="%s">\n' % id
                 fmarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
-                fmarker += '\n</footnote>\n'
+                fmarker += b'\n</footnote>\n'
                 r += fmarker
                 fnote_ids = fnote_ids[id_len+4:]
 
@@ -338,18 +338,18 @@ class EreaderProcessor(object):
 
         # now handle sidebar pages
         if self.num_sidebar_pages > 0:
-            r += '\n'
+            r += b'\n'
             # the record 0 of the sidebar section must pass through the Xor Table to make it useful
             sect = self.section_reader(self.first_sidebar_page)
             sbar_ids = deXOR(sect, 0, self.xortable)
             # the remaining records of the sidebar sections need to be decoded with the content_key and zlib inflated
             des = DES.new(fixKey(self.content_key), DES.MODE_ECB)
             for i in range(1,self.num_sidebar_pages):
-                id_len = ord(sbar_ids[2])
+                id_len = sbar_ids[2]
                 id = sbar_ids[3:3+id_len]
-                smarker = '<sidebar id="%s">\n' % id
+                smarker = b'<sidebar id="%s">\n' % id
                 smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_sidebar_page + i)))
-                smarker += '\n</sidebar>\n'
+                smarker += b'\n</sidebar>\n'
                 r += smarker
                 sbar_ids = sbar_ids[id_len+4:]
 

DeDRM_plugin/ineptpdf.py

@@ -1624,7 +1624,7 @@ class PDFDocument(object):
             print("ebx_V is %d  and ebx_type is %d" % (ebx_V, ebx_type))
             print("length is %d and len(bookkey) is %d" % (length, len(bookkey)))
             if len(bookkey) > 0:
-                print("bookkey[0] is %d" % ord(bookkey[0]))
+                print("bookkey[0] is %d" % bookkey[0])
             if ebx_V == 3:
                 V = 3
             else:

DeDRM_plugin/ion.py

@@ -420,7 +420,7 @@ class BinaryIonParser(object):
         _assert(self.localremaining <= 8, "Decimal overflow")
 
         signed = False
-        b = [ord(x) for x in self.read(self.localremaining)]
+        b = list(self.read(self.localremaining))
         if (b[0] & 0x80) != 0:
             b[0] = b[0] & 0x7F
             signed = True
@@ -657,7 +657,7 @@ class BinaryIonParser(object):
 
         result = ""
         for i in b:
-            result += ("%02x " % ord(i))
+            result += ("%02x " % i)
 
         if len(result) > 0:
             result = result[:-1]

DeDRM_plugin/kgenpids.py

@@ -14,7 +14,6 @@ __version__ = '3.0'
 #  3.0   - Python 3 for calibre 5.0
 
 
-import sys
 import os, csv
 import binascii
 import zlib
@@ -69,7 +68,7 @@ def encodeHash(data,map):
 
 # Decode the string in data with the characters in map. Returns the decoded bytes
 def decode(data,map):
-    result = ''
+    result = b''
     for i in range (0,len(data)-1,2):
         high = map.find(data[i])
         low = map.find(data[i+1])

DeDRM_plugin/utilities.py

@@ -3,8 +3,6 @@
 
 #@@CALIBRE_COMPAT_CODE@@
 
-import sys
-
 __license__ = 'GPL v3'
 
 def uStrCmp (s1, s2, caseless=False):
@@ -29,8 +27,7 @@ class SafeUnbuffered:
         if self.encoding == None:
             self.encoding = "utf-8"
     def write(self, data):
-        if isinstance(data,str) or isinstance(data,unicode):
-            # str for Python3, unicode for Python2
+        if isinstance(data,str):
             data = data.encode(self.encoding,"replace")
         try:
             buffer = getattr(self.stream, 'buffer', self.stream)

DeDRM_plugin/zipfilerugged.py

@@ -676,8 +676,7 @@ class ZipFile:
         self.comment = b''
 
         # Check if we were passed a file-like object
-        # "str" is python3, "unicode" is python2
-        if isinstance(file, str) or isinstance(file, unicode):
+        if isinstance(file, str):
             self._filePassed = 0
             self.filename = file
             modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'}