Removed prints and extract function from init module

ebook_converter/ebooks/__init__.py

@@ -5,11 +5,9 @@ from various formats.
 import numbers
 import os
 import re
-import sys
 
 from lxml import etree
 
-from ebook_converter import prints
 from ebook_converter.ebooks.chardet import xml_to_unicode
 
 
@@ -123,13 +121,14 @@ def render_html_data(path_to_html, width, height):
     result = {}
 
     def report_error(text=''):
-        prints('Failed to render', path_to_html, 'with errors:',
-               file=sys.stderr)
+        __import__('pdb').set_trace()
+        print(f'Failed to render {path_to_html}')
+        # file=sys.stderr)
         if text:
-            prints(text, file=sys.stderr)
+            print(text)  # , file=sys.stderr)
         if result and result['stdout_stderr']:
             with open(result['stdout_stderr'], 'rb') as f:
-                prints(f.read(), file=sys.stderr)
+                print(f.read())  # , file=sys.stderr)
 
     with TemporaryDirectory('-render-html') as tdir:
         try:

ebook_converter/ebooks/conversion/plumber.py

@@ -14,7 +14,6 @@ from ebook_converter.ebooks.conversion.preprocess import HTMLPreProcessor
 from ebook_converter.ptempfile import PersistentTemporaryDirectory
 from ebook_converter.utils.date import parse_date
 from ebook_converter.utils.zipfile import ZipFile
-from ebook_converter import extract, walk
 from ebook_converter import constants
 from ebook_converter.constants_old import filesystem_encoding
 
@@ -694,11 +693,6 @@ OptionRecommendation(name='search_replace',
             input_fmt = 'epub'
         self.archive_input_tdir = None
         self.changed_options = set()
-        if input_fmt in ARCHIVE_FMTS:
-            self.log('Processing archive...')
-            tdir = PersistentTemporaryDirectory('_pl_arc')
-            self.input, input_fmt = self.unarchive(self.input, tdir)
-            self.archive_input_tdir = tdir
         if os.access(self.input, os.R_OK):
             nfp = run_plugins_on_preprocess(self.input, input_fmt)
             if nfp != self.input:
@@ -761,25 +755,6 @@ OptionRecommendation(name='search_replace',
         if merge_plugin_recs:
             self.merge_plugin_recommendations()
 
-    @classmethod
-    def unarchive(self, path, tdir):
-        extract(path, tdir)
-        files = list(walk(tdir))
-        files = [f if isinstance(f, str) else f.decode(filesystem_encoding)
-                for f in files]
-        from ebook_converter.customize.ui import available_input_formats
-        fmts = set(available_input_formats())
-        fmts -= {'htm', 'html', 'xhtm', 'xhtml'}
-        fmts -= set(ARCHIVE_FMTS)
-
-        for ext in fmts:
-            for f in files:
-                if f.lower().endswith('.'+ext):
-                    if ext in ['txt', 'rtf'] and os.stat(f).st_size < 2048:
-                        continue
-                    return f, ext
-        return self.find_html_index(files)
-
     @classmethod
     def find_html_index(self, files):
         '''

ebook_converter/ebooks/html/input.py

@@ -8,7 +8,7 @@ import sys
 import urllib.parse
 
 from ebook_converter.ebooks.chardet import detect_xml_encoding
-from ebook_converter import unicode_path, replace_entities
+from ebook_converter import replace_entities
 
 
 class Link(object):

ebook_converter/ebooks/html/to_zip.py

@@ -24,7 +24,6 @@ class HTML2ZIP(FileTypePlugin):
 
     def run(self, htmlfile):
         import codecs
-        from ebook_converter import prints
         from ebook_converter.ptempfile import TemporaryDirectory
         from ebook_converter.gui2.convert.gui_conversion import gui_convert
         from ebook_converter.customize.conversion import OptionRecommendation
@@ -40,7 +39,8 @@ class HTML2ZIP(FileTypePlugin):
                     try:
                         codecs.lookup(enc)
                     except Exception:
-                        prints('Ignoring invalid input encoding for HTML:', enc)
+                        print('Ignoring invalid input encoding for HTML: %s',
+                              enc)
                     else:
                         recs.append(['input_encoding', enc, OptionRecommendation.HIGH])
                 if bf == 'bf':

ebook_converter/ebooks/metadata/__init__.py

@@ -8,7 +8,7 @@ import re
 import sys
 import urllib.parse
 
-from ebook_converter import prints, force_unicode
+from ebook_converter import force_unicode
 from ebook_converter.utils.config_base import tweaks
 from ebook_converter.polyglot.urllib import unquote
 
@@ -16,8 +16,8 @@ from ebook_converter.polyglot.urllib import unquote
 try:
     _author_pat = re.compile(tweaks['authors_split_regex'])
 except Exception:
-    prints('Author split regexp:', tweaks['authors_split_regex'],
-           'is invalid, using default')
+    print(f"Author split regexp: {tweaks['authors_split_regex']}, is invalid, "
+          f"using default")
     _author_pat = re.compile(r'(?i),?\s+(and|with)\s+')
 
 

ebook_converter/ebooks/metadata/book/base.py

@@ -1,6 +1,5 @@
 import copy, traceback
 
-from ebook_converter import prints
 from ebook_converter.constants_old import DEBUG
 from ebook_converter.ebooks.metadata.book import (SC_COPYABLE_FIELDS,
         SC_FIELDS_COPY_NOT_NULL, STANDARD_METADATA_FIELDS,
@@ -453,12 +452,12 @@ class Metadata(object):
     # Old Metadata API {{{
     def print_all_attributes(self):
         for x in STANDARD_METADATA_FIELDS:
-            prints('%s:'%x, getattr(self, x, 'None'))
+            print('%s:' % x, getattr(self, x, 'None'))
         for x in self.custom_field_keys():
             meta = self.get_user_metadata(x, make_copy=False)
             if meta is not None:
-                prints(x, meta)
-        prints('--------------')
+                print(x, meta)
+        print('--------------')
 
     def smart_update(self, other, replace_metadata=False):
         '''

ebook_converter/ebooks/metadata/fb2.py

@@ -12,7 +12,7 @@ from lxml import etree
 from ebook_converter.utils.date import parse_only_date
 from ebook_converter.utils.img import save_cover_data_to
 from ebook_converter.utils.imghdr import identify
-from ebook_converter import prints, force_unicode
+from ebook_converter import force_unicode
 from ebook_converter.ebooks.metadata import MetaInformation, check_isbn
 from ebook_converter.ebooks.chardet import xml_to_unicode
 from ebook_converter.polyglot.binary import as_base64_unicode
@@ -237,8 +237,8 @@ def _parse_cover_data(root, imgid, mi, ctx):
                 fmt = identify(cdata)[0]
                 mi.cover_data = (fmt, cdata)
         else:
-            prints("WARNING: Unsupported coverpage mime-type '%s' (id=#%s)" %
-                   (mimetype, imgid))
+            print(f"WARNING: Unsupported coverpage mime-type '{mimetype}' "
+                  f"(id=#{imgid})")
 
 
 def _parse_tags(root, mi, ctx):

ebook_converter/ebooks/metadata/opf2.py

@@ -32,7 +32,6 @@ from ebook_converter.ebooks.metadata import string_to_authors, \
 from ebook_converter.ebooks.metadata.book.base import Metadata
 from ebook_converter.utils.date import parse_date, isoformat
 from ebook_converter.utils.localization import get_lang, canonicalize_lang
-from ebook_converter import prints
 from ebook_converter.utils.cleantext import clean_ascii_chars, clean_xml_chars
 from ebook_converter.utils.config import tweaks
 from ebook_converter.polyglot.urllib import unquote
@@ -516,7 +515,7 @@ def serialize_user_metadata(metadata_elem, all_user_metadata,
             fm = object_to_unicode(fm)
             fm = json.dumps(fm, default=to_json, ensure_ascii=False)
         except Exception:
-            prints('Failed to write user metadata:', name)
+            print('Failed to write user metadata: {name}')
             traceback.print_exc()
             continue
         meta = metadata_elem.makeelement('meta')
@@ -671,7 +670,7 @@ class OPF(object):  # {{{
                 decode_is_multiple(fm)
                 temp.set_user_metadata(name, fm)
             except Exception:
-                prints('Failed to read user metadata:', name)
+                print('Failed to read user metadata: {name}')
                 traceback.print_exc()
                 continue
         self._user_metadata_ = temp.get_all_user_metadata(True)

ebook_converter/ebooks/metadata/opf3.py

@@ -6,7 +6,6 @@ import re
 from lxml import etree
 
 from ebook_converter import constants as const
-from ebook_converter import prints
 from ebook_converter.ebooks.metadata import authors_to_string
 from ebook_converter.ebooks.metadata import check_isbn
 from ebook_converter.ebooks.metadata import string_to_authors
@@ -923,7 +922,7 @@ def read_user_metadata2(root, remove_tags=False):
             decode_is_multiple(fm)
             ans[name] = fm
         except Exception:
-            prints('Failed to read user metadata:', name)
+            print('Failed to read user metadata: {name}')
             import traceback
             traceback.print_exc()
             continue

ebook_converter/ebooks/metadata/pdf.py

@@ -4,7 +4,6 @@ Read meta information from PDF files
 import os, subprocess, shutil, re
 from functools import partial
 
-from ebook_converter import prints
 from ebook_converter.ptempfile import TemporaryDirectory
 from ebook_converter.ebooks.metadata import (
     MetaInformation, string_to_authors, check_isbn, check_doi)
@@ -39,12 +38,12 @@ def read_info(outputdir, get_cover):
         raw = subprocess.check_output([pdfinfo, '-enc', 'UTF-8', '-isodates',
                                        source_file])
     except subprocess.CalledProcessError as e:
-        prints('pdfinfo errored out with return code: %d'%e.returncode)
+        print(f'pdfinfo errored out with return code: {e.returncode}')
         return None
     try:
         info_raw = raw.decode('utf-8')
     except UnicodeDecodeError:
-        prints('pdfinfo returned no UTF-8 data')
+        print('pdfinfo returned no UTF-8 data')
         return None
 
     for line in info_raw.splitlines():
@@ -63,7 +62,8 @@ def read_info(outputdir, get_cover):
     try:
         raw = subprocess.check_output([pdfinfo, '-meta', source_file]).strip()
     except subprocess.CalledProcessError as e:
-        prints('pdfinfo failed to read XML metadata with return code: %d'%e.returncode)
+        print('pdfinfo failed to read XML metadata with return code: '
+              f'{e.returncode}')
     else:
         parts = re.split(br'^Metadata:', raw, 1, flags=re.MULTILINE)
         if len(parts) > 1:
@@ -77,7 +77,7 @@ def read_info(outputdir, get_cover):
             subprocess.check_call([pdftoppm, '-singlefile', '-jpeg',
                                    '-cropbox', source_file, cover_file])
         except subprocess.CalledProcessError as e:
-            prints('pdftoppm errored out with return code: %d'%e.returncode)
+            print('pdftoppm errored out with return code: {e.returncode}')
 
     return ans
 

ebook_converter/ebooks/metadata/xmp.py

@@ -4,11 +4,11 @@ import itertools
 import json
 import re
 import sys
+import traceback
 
 from lxml import etree
 from lxml.builder import ElementMaker
 
-from ebook_converter import prints
 from ebook_converter.ebooks.metadata import check_isbn, check_doi
 from ebook_converter.ebooks.metadata.book.base import Metadata
 from ebook_converter.ebooks.metadata.opf2 import dump_dict
@@ -192,7 +192,7 @@ def read_user_metadata(mi, root):
                             mi.set_user_metadata(name, fm)
                             fields.add(name)
                         except Exception:
-                            prints('Failed to read user metadata:', name)
+                            print(f'Failed to read user metadata: {name}')
                             import traceback
                             traceback.print_exc()
 
@@ -467,8 +467,7 @@ def create_user_metadata(calibre, all_user_metadata):
             fm = object_to_unicode(fm)
             fm = json.dumps(fm, default=to_json, ensure_ascii=False)
         except Exception:
-            prints('Failed to write user metadata:', name)
-            import traceback
+            print('Failed to write user metadata: {name}')
             traceback.print_exc()
             continue
         li = bag.makeelement(expand('rdf:li'))

ebook_converter/ebooks/pdf/pdftohtml.py

@@ -7,7 +7,7 @@ import sys
 
 from lxml import etree
 
-from ebook_converter import CurrentDir, xml_replace_entities, prints
+from ebook_converter import CurrentDir, xml_replace_entities
 from ebook_converter.constants_old import isbsd, islinux, isosx
 from ebook_converter.ebooks import ConversionError, DRMError
 from ebook_converter.ebooks.chardet import xml_to_unicode
@@ -78,8 +78,8 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
             raise ConversionError('pdftohtml failed with return code: '
                                   '%d\n%s' % (ret, out))
         if out:
-            prints("pdftohtml log:")
-            prints(out)
+            print("pdftohtml log:")
+            print(out)
         if not os.path.exists(index) or os.stat(index).st_size < 100:
             raise DRMError()