Merge pull request #11 from letuananh/dev-0.1.1

texttaglib 0.1.1 stable release

.gitignore

@@ -1,6 +1,4 @@
 .env_python3/
-chirptext
-puchikarui
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

.gitmodules

@@ -0,0 +1,8 @@
+[submodule "modules/chirptext"]
+	path = modules/chirptext
+	url = https://github.com/letuananh/chirptext
+	branch = chirptext-0.1
+[submodule "modules/puchikarui"]
+	path = modules/puchikarui
+	url = https://github.com/letuananh/puchikarui
+	branch = puchikarui-0.1

MANIFEST.in

@@ -2,3 +2,5 @@ include README.md
 include LEGACY.md
 include requirements*.txt
 recursive-include texttaglib/data *.sql
+recursive-include texttaglib/chirptext/data/luke/swadesh *.txt
+recursive-include texttaglib/chirptext/data/sino *.csv

README.md

@@ -1,12 +1,14 @@
 # texttaglib
 
+a Python library for managing and annotating text corpuses in different formats (ELAN, TIG, TTL, et cetera).
+
 [![ReadTheDocs Badge](https://readthedocs.org/projects/texttaglib/badge/?version=latest&style=plastic)](https://texttaglib.readthedocs.io/)
 [![Total alerts](https://img.shields.io/lgtm/alerts/g/letuananh/texttaglib.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/letuananh/texttaglib/alerts/)
 [![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/letuananh/texttaglib.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/letuananh/texttaglib/context:python)
 
 ## Warning
 
-⚠️ THIS PROJECT IS ARCHIVED. ALL FUTURE DEVELOPMENT WILL BE ON [speach](https://pypi.org/project/speach/) LIBRARY ⚠️
+⚠️ `texttaglib` package is now in maintenance mode for supporting legacy software only. All new development will be moved to [speach](https://pypi.org/project/speach/) library.
 
 Migration from `texttaglib` to `speach` should be trivial
 
@@ -26,4 +28,19 @@ pip install texttaglib
 pip install speach
 ```
 
-- For more information, please visit: https://github.com/neocl/speach
+For more information, please visit: https://github.com/neocl/speach
+
+## Legacy
+
+texttaglib legacy releases (>= 0.1.1, < 0.2) use embedded chirptext-0.1 and puchikarui-0.1 for supporting legacy APIs.
+
+Here is the sample code:
+
+```python
+from texttaglib import ttl
+from texttaglib.chirptext import chio
+from texttaglib.chirptext import deko
+from texttaglib.puchikarui import Schema
+```
+
+Legacy documentation: https://texttaglib.readthedocs.io

dev_config.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+
+bold=$(tput bold)
+normal=$(tput sgr0)
+WORKSPACE_FOLDER=~/workspace
+py3=`python -c "import sys; print('1' if sys.version_info >= (3,0) else '0')"`
+
+function link_folder {
+    FOLDER_PATH=$1
+    SYMLINK_NAME=$2
+    if [ ! -d ${FOLDER_PATH} ]; then
+        echo "WARNING: Target folder ${bold}${FOLDER_PATH}${normal} does not exist"
+    elif [ ! -d ${SYMLINK_NAME} ]; then
+	ln -sv ${FOLDER_PATH} ${SYMLINK_NAME}
+    else
+	echo "Folder ${bold}${SYMLINK_NAME}${normal} exists."
+    fi
+}
+
+function link_file {
+    TARGET_FILE=$1
+    SYMLINK_NAME=$2
+    if [ ! -f ${TARGET_FILE} ]; then
+        echo "WARNING: Target file ${bold}${TARGET_FILE}${normal} does not exist"
+    elif [ ! -f ${SYMLINK_NAME} ]; then
+	ln -sv ${TARGET_FILE} ${SYMLINK_NAME}
+    else
+	echo "File ${bold}${SYMLINK_NAME}${normal} exists."
+    fi
+}
+
+if [ ${py3} -eq 0 ]; then
+    echo "+-------------------------------+"
+    echo "| WARNING: Python 3 is required |"
+    echo "+-------------------------------+"
+fi
+
+# init submodules
+git submodule init && git submodule update
+
+# prerequisite packages
+pip install -r requirements.txt -qq
+
+link_folder `readlink -f ./modules/chirptext/chirptext` texttaglib/chirptext
+link_folder `readlink -f ./modules/puchikarui/puchikarui` texttaglib/puchikarui
+

docs/index.rst

@@ -3,11 +3,49 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Welcome to texttaglib's documentation!
-======================================
+texttaglib's documentation!
+===========================
+
+.. warning::
+    ⚠️ THIS PROJECT HAS BEEN RENAMED AND ARCHIVED. ALL FUTURE DEVELOPMENT WILL BE ON
+    `speach <https://pypi.org/project/speach/>`__ LIBRARY ⚠️
+
+Migration to speach
+-------------------
+
+    Migration from ``texttaglib`` to `speach <https://speach.readthedocs.io/>`_ should be trivial
+
+
+.. code:: python
+
+    # just change import statements from something like
+    from texttaglib import elan
+    # to the new package name
+    from speach import elan
+
+Installation
+
+.. code:: bash
+
+    # change
+    pip install texttaglib 
+    # into
+    pip install speach
+
+-  For more information, please visit: https://speach.readthedocs.io/
+
+(Legacy) Introduction
+---------------------
 
 texttaglib is a Python library for managing and annotating text corpuses in different formats.
 
+.. image:: https://readthedocs.org/projects/texttaglib/badge/?version=latest&style=plastic
+   :target: https://texttaglib.readthedocs.io/
+.. image:: https://img.shields.io/lgtm/alerts/g/letuananh/texttaglib.svg?logo=lgtm&logoWidth=18
+   :target: https://lgtm.com/projects/g/letuananh/texttaglib/alerts/
+.. image:: https://img.shields.io/lgtm/grade/python/g/letuananh/texttaglib.svg?logo=lgtm&logoWidth=18
+   :target: https://lgtm.com/projects/g/letuananh/texttaglib/context:python
+
 Main functions are:
 
 -  Multiple storage formats (text files, JSON files, SQLite databases)
@@ -24,8 +62,6 @@ texttaglib is availble on PyPI.
 .. code:: bash
 
    pip install texttaglib
-   # or more explicit
-   python3 -m pip install texttaglib
 
 Basic usage
 -----------

docs/requirements.txt

@@ -1,2 +1,3 @@
 chirptext >= 0.1a18
 puchikarui
+Sphinx

requirements.txt

@@ -1,2 +0,0 @@
-chirptext >= 0.1a18
-puchikarui

setup.py

@@ -66,7 +66,7 @@ def read(*filenames, **kwargs):
         "Bug Tracker": "https://github.com/letuananh/texttaglib/issues",
         "Source Code": "https://github.com/letuananh/texttaglib/"
     },
-    keywords="nlp",
+    keywords=["nlp", "annotation", "text", "corpus", "linguistics", "ELAN", "transcription"],
     license=pkg_info['__license__'],
     author=pkg_info['__author__'],
     tests_require=requirements,
@@ -76,14 +76,17 @@ def read(*filenames, **kwargs):
     long_description=long_description,
     long_description_content_type='text/markdown',
     packages=['texttaglib',
-              'texttaglib.data'],
-    package_data={'texttaglib': ['data/*.sql', 'data/*.gz']},
+              'texttaglib.data',
+              'texttaglib.chirptext',
+              'texttaglib.puchikarui'],
+    package_data={'texttaglib': ['data/*.sql', 'data/*.gz'],
+                  'texttaglib.chirptext': ['data/luke/swadesh/*.txt', 'data/sino/*.csv']},
     include_package_data=True,
     platforms='any',
     test_suite='test',
     # Reference: https://pypi.python.org/pypi?%3Aaction=list_classifiers
     classifiers=['Programming Language :: Python',
-                 'Development Status :: 2 - Pre-Alpha',
+                 'Development Status :: {}'.format(pkg_info['__status__']),
                  'License :: OSI Approved :: {}'.format(pkg_info['__license__']),
                  'Environment :: Plugins',
                  'Intended Audience :: Education',

test/__init__.py

@@ -14,7 +14,7 @@
 # Homepage: https://github.com/letuananh/texttaglib
 
 import os
-from chirptext.cli import setup_logging
+from texttaglib.chirptext.cli import setup_logging
 
 TEST_DIR = os.path.dirname(__file__)
 TEST_DATA = os.path.join(TEST_DIR, 'data')

test/test_ttlig.py

@@ -41,8 +41,8 @@
 import logging
 from collections import OrderedDict
 
-from chirptext import chio
-from chirptext import deko
+from texttaglib.chirptext import chio
+from texttaglib.chirptext import deko
 
 from texttaglib import ttl
 from texttaglib import ttlig

texttaglib/__init__.py

@@ -36,7 +36,7 @@
 from .__version__ import __credits__, __license__, __description__, __url__
 from .__version__ import __version_major__, __version_long__, __version__, __status__
 
-from chirptext import texttaglib as ttl
+from .chirptext import texttaglib as ttl
 from texttaglib.sqlite import TTLSQLite
 
 

texttaglib/__main__.py

@@ -33,11 +33,10 @@
 
 import os
 import logging
-from lxml import etree
 
-from chirptext import TextReport, FileHelper
-from chirptext import chio
-from chirptext.cli import CLIApp, setup_logging
+from .chirptext import TextReport, FileHelper
+from .chirptext import chio
+from .chirptext.cli import CLIApp, setup_logging
 
 from texttaglib import ttl, TTLSQLite, ttlig, orgmode
 from texttaglib.elan import parse_eaf_stream
@@ -185,21 +184,28 @@ def make_text(sent, delimiter=' '):
 
 def make_html(cli, args):
     ''' Convert TTL to HTML '''
-    print("Reading document ...")
-    ttl_doc = ttl.Document.read_ttl(args.ttl)
-    output = TextReport(args.output)
-    doc_node = etree.Element('doc')
-    for sent in ttl_doc:
-        sent_node = etree.SubElement(doc_node, 'sent')
-        text_node = etree.XML(make_text(sent, delimiter=args.delimiter))
-        sent_node.append(text_node)
-        if sent.get_tag('translation'):
+    _LXML_AVAILABLE = False
+    try:
+        from lxml import etree
+        _LXML_AVAILABLE = True
+    except Exception:
+        print("lxml is required for this function")
+    if _LXML_AVAILABLE:
+        print("Reading document ...")
+        ttl_doc = ttl.Document.read_ttl(args.ttl)
+        output = TextReport(args.output)
+        doc_node = etree.Element('doc')
+        for sent in ttl_doc:
+            sent_node = etree.SubElement(doc_node, 'sent')
+            text_node = etree.XML(make_text(sent, delimiter=args.delimiter))
+            sent_node.append(text_node)
+            if sent.get_tag('translation'):
+                etree.SubElement(sent_node, 'br')
+                trans_node = etree.SubElement(sent_node, 'trans')
+                trans_node.text = sent.get_tag('translation').label
+            etree.SubElement(sent_node, 'br')
             etree.SubElement(sent_node, 'br')
-            trans_node = etree.SubElement(sent_node, 'trans')
-            trans_node.text = sent.get_tag('translation').label
-        etree.SubElement(sent_node, 'br')
-        etree.SubElement(sent_node, 'br')
-    output.write(etree.tostring(doc_node, encoding='unicode', pretty_print=not args.compact))
+        output.write(etree.tostring(doc_node, encoding='unicode', pretty_print=not args.compact))
 
 
 def sec_str(a_float):

texttaglib/__version__.py

@@ -6,10 +6,10 @@
 __copyright__ = "Copyright (c) 2018, texttaglib, Le Tuan Anh"
 __credits__ = []
 __license__ = "MIT License"
-__description__ = "Python library for managing and annotating textual corpus using TextTagLib (TTL) format"
+__description__ = "Python library for managing and annotating text corpuses in different formats (ELAN, TIG, TTL, et cetera)"
 __url__ = "https://github.com/letuananh/texttaglib"
 __maintainer__ = "Le Tuan Anh"
-__version_major__ = "0.1"
+__version_major__ = "0.1.1"
 __version__ = "{}".format(__version_major__)
 __version_long__ = "{}".format(__version_major__)
-__status__ = "Prototype"
+__status__ = "5 - Production/Stable"

texttaglib/chirptext

@@ -0,0 +1 @@
+/home/tuananh/workspace/texttaglib/modules/chirptext/chirptext

texttaglib/elan.py

@@ -34,8 +34,8 @@
 from typing import List, Tuple
 import xml.etree.ElementTree as ET
 
-from chirptext import DataObject
-from chirptext import chio
+from .chirptext import DataObject
+from .chirptext import chio
 
 from .vtt import sec2ts, ts2sec
 

texttaglib/orgmode.py

@@ -39,7 +39,7 @@
 import os
 import logging
 
-from chirptext import chio
+from .chirptext import chio
 
 
 # ----------------------------------------------------------------------

texttaglib/puchikarui

@@ -0,0 +1 @@
+/home/tuananh/workspace/texttaglib/modules/puchikarui/puchikarui

texttaglib/sqlite.py

@@ -33,9 +33,9 @@
 
 import logging
 
-from chirptext import DataObject
-from puchikarui import Schema, with_ctx
-from texttaglib import ttl
+from .puchikarui import Schema, with_ctx
+from .chirptext import DataObject
+from .chirptext import ttl
 from .data import INIT_TTL_SQLITE
 
 

texttaglib/ttlig.py

@@ -37,11 +37,11 @@
 from collections import OrderedDict
 import warnings
 
-from chirptext import DataObject, piter
-from chirptext import chio
-from chirptext.deko import is_kana, parse
+from .chirptext import DataObject, piter
+from .chirptext import chio
+from .chirptext.deko import is_kana, parse
+from .chirptext import ttl
 
-from texttaglib import ttl
 
 
 # ----------------------------------------------------------------------