Merge pull request #48 from deborahgu/iamaster

Incorporated all internetarchive fork changes, with some efficiency, PEP8 modifications.

.gitignore

@@ -1,5 +1,6 @@
 # Byte-compiled / optimized / DLL files
 __pycache__/
+.pytest_cache/
 *.py[cod]
 *$py.class
 

MANIFEST.in

@@ -0,0 +1 @@
+include requirements.txt

README.rst

@@ -9,7 +9,7 @@ Introduction
 This module transforms ABBYY XML documents, generated by ABBYY FineReader 10,
 into primitively accessible ePub 3. The code is optimized for ABBYY XML
 documents created by the Internet Archive, though it may work for other ABBYY
-XML as well. 
+XML as well.
 
 Features
 ========
@@ -37,45 +37,43 @@ Requirements
 
 * Python 3
 * If running epubcheck, a Java Runtime environment
-* If running DAISY Ace, Node.js
 * If using Kakadu, `install the binaries <http://kakadusoftware.com/downloads/>`_ and add the your  PATH and LD_LIBRARY_PATH
 
 Usage
 =====
 
 From within a Python program:
 
-.. code:: python 
+.. code:: python
 
     from abbyy_to_epub3 import create_epub
     book = create_epub.Ebook('docname')  # See *Assumptions* below.
     book.craft_epub()
 
 From the shell:
 
-.. code:: bash 
+.. code:: bash
 
      abbyy2epub docname     # See *Assumptions* below.
 
 The available command line arguments are:
 
 .. code:: bash 
 
-    usage: abbyy2epub [-h] [-d] [--epubcheck] [--ace] docname
+    usage: abbyy2epub [-h] [-d] [--epubcheck] docname
 
     Process an ABBYY file into an EPUB
-    
+
     positional arguments:
       item_dir         The file path where this item's files are kept.
       item_identifier  The unique ID of this item.
       item_bookpath    The prefix to a specific book within an item.In a simple
-                   book, usually the same as the item_identifier.
-    
+                       book, usually the same as the item_identifier.
+
     optional arguments:
       -h, --help   show this help message and exit
       -d, --debug  Show debugging information
       --epubcheck  Run EpubCheck on the newly created EPUB
-      --ace        Run DAISY Ace on the newly created EPUB
 
 
 System dependencies
@@ -85,47 +83,39 @@ If you'd like to run `epubcheck <https://github.com/IDPF/epubcheck>`_, there
 are certain system dependencies.  Depending on running environment, these may
 need to be manually installed.  On Ubuntu, I installed these with:
 
-.. code:: bash 
+.. code:: bash
 
     sudo apt-get install default-jre libpython3-dev
 
-If you'd like to run the DAISY Ace accessibility checker, you'll also need
-Node.js and Ace. On Ubuntu, I installed these with:
-
-.. code:: bash 
-
-    sudo apt-get install nodejs
-    sudo npm install ace-core -g
-
-If Ace successfully installed, you should be able to run:
-
-.. code:: bash 
-
-   ace --help
-
-at the command line. This should display usage information. For more
-information see the `Ace Getting Started Guide
-<http://inclusivepublishing.org/toolbox/accessibility-checker/getting-started/>`.
 
 Installation
 ============
 
 This package can be installed on your local system. From the directory
 containing setup.py:
 
-.. code:: bash 
+.. code:: bash
 
     pip install -r requirements.txt
     python setup.py develop
     pip install .
 
 You can rebuild the documentation, which is generated with Sphinx.
 
-.. code:: bash 
+.. code:: bash
 
    cd docs
    make html
 
+Deploying at the Internet Archive
+===================
+
+Before deploying, make sure you bump the version of the package in `__init__.py`. Then, run the `upload.sh` script in the root of the repository and enter the appropriate Internet Archive credentials when prompted.
+
+You can test that the package has been installed correctly by going to https://devpi.archive.org or by running `$ pip3 install --upgrade -i https://petaboxdevpi:{PASSWORD}@devpi.archive.org/books/formats abbyy_to_epub3`.
+
+Note that `petaboxdevpi:{PASSWORD}` is not needed inside IA network`
+
 Testing
 ===================
 
@@ -143,11 +133,9 @@ specific book. Given a datanode and an `item_dir` of an item, all the
 constituent files for a book can be constructed using `item_identifier` and
 `item_bookpath` in the following ways:
 
-In order to access the files of an item, you need to know:
-
-# The `item_identifier` (the unique ID of this item)
-# The `item_dir` is the file path where this items files are kept
-# The `item_bookpath` is name of the particular book file, often the same as `item_identifier`
+- The `item_identifier` (the unique ID of this item)
+- The `item_dir` is the file path where this items files are kept
+- The `item_bookpath` is name of the particular book file, often the same as `item_identifier`
 
 The structure is assumed to be:
 

abbyy_to_epub3/__init__.py

@@ -0,0 +1,4 @@
+
+__title__ = 'abbyy_to_epub3'
+__version__ = '1.6.5'
+__author__ = '@deborahgu'

abbyy_to_epub3/commandline.py

@@ -19,7 +19,7 @@
 import argparse
 import logging
 
-from abbyy_to_epub3 import create_epub
+from abbyy_to_epub3.create_epub import Ebook
 
 logger = logging.getLogger(__name__)
 
@@ -51,16 +51,22 @@ def main():
         ),
     )
     parser.add_argument(
-        '--epubcheck',
-        default=False,
-        action='store_true',
-        help='Run EpubCheck on the newly created EPUB',
+        '-o',
+        '--out',
+        default=None,
+        help='Output path for epub',
     )
     parser.add_argument(
-        '--ace',
-        default=False,
-        action='store_true',
-        help='Run DAISY Ace on the newly created EPUB',
+        '--tmpdir',
+        default=None,
+        help='Specify custom path for tmp abbyy and jp2 files'
+    )
+    parser.add_argument(
+        '--epubcheck',
+        nargs='?',
+        const=Ebook.DEFAULT_EPUBCHECK_LEVEL,
+        help='Run EpubCheck on the newly created EPUB. '
+        'Options: `warning` & worse (default), `error` & worse, `fatal` only',
     )
     args = parser.parse_args()
 
@@ -69,14 +75,16 @@ def main():
         if debug:
             logger.addHandler(logging.StreamHandler())
             logger.setLevel(logging.DEBUG)
-        book = create_epub.Ebook(
+        book = Ebook(
             args.item_dir,
             args.item_identifier,
             args.item_bookpath,
             debug=debug,
-            args=args,
+            epubcheck=args.epubcheck,
+        )
+        book.craft_epub(
+            epub_outfile=args.out or 'out.epub', tmpdir=args.tmpdir
         )
-        book.craft_epub()
 
 
 if __name__ == "__main__":

abbyy_to_epub3/constants.py

@@ -1,4 +1,4 @@
-# Copyright 2017 Deborah Kaplan
+# Copyright 2017 Deborah Kaplan
 #
 # This file is part of Abbyy-to-epub3.
 # Source code is available at <https://github.com/deborahgu/abbyy-to-epub3>.
@@ -31,7 +31,6 @@
 # on each block, just use a custom pagetype for anything where
 # "addToAccessFormats" is set to false. This is 'skippable.'
 skippable_pages = [
-    'cover',
     'copyright',
     'color card',
     'skippable',