Poetry config

.github/workflows/ci-tests.yml

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: ["3.7", "3.8", "3.9", "3.10"]
 
     steps:
     - uses: actions/checkout@v2

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.3.0
     hooks:
     -   id: trailing-whitespace
         # Leave demo-files unaltered after download from BL website.
@@ -12,18 +12,23 @@ repos:
     -   id: check-xml
     -   id: check-added-large-files
 -   repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 22.6.0
     hooks:
     -   id: black
 -   repo: https://github.com/pre-commit/mirrors-autopep8
-    rev: 'v1.6.0'  # Use the sha / tag you want to point at
+    rev: v1.6.0  # Use the sha / tag you want to point at
     hooks:
     -   id: autopep8
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v0.960'  # Use the sha / tag you want to point at
+    rev: v0.971  # Use the sha / tag you want to point at
     hooks:
     -   id: mypy
-# -   repo: https://github.com/pre-commit/mirrors-isort
-#     rev: v5.10.1
-#     hooks:
-#     -   id: isort
+-   repo: https://github.com/pre-commit/mirrors-isort
+    rev: v5.10.1
+    hooks:
+    -   id: isort
+-   repo: https://github.com/hadialqattan/pycln
+    rev: v1.2.5
+    hooks:
+    -   id: pycln
+        args: [--config=pyproject.toml]

CHANGELOG.md

@@ -3,24 +3,83 @@ All notable changes to this software will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
-Please maintain both this file AND the README.md file.
+Please maintain both this file AND the `README.md` file.
 
-## [Unreleased]
+## [0.3.4]
 
 ### Added
-* Added this changelog file.
-* Established use of [Semantic Versioning](https://semver.org/spec/v2.0.0.html) for this project.
-* Added a separate 'CONTRIBUTING.md' doc for software developers notes.
-* Added a separate copyright notice for example datasets
+ * Added `PyPI` version and `MIT` license badges to `README.md`
+ * Added `pytest-cov` with default options to assess documentation
+ * Added `isort` to `.pre-commit-config.yaml` to sort import consistency
+ * Added `pycln` to  `.pre-commit-config.yaml` to check unused imports
+ * Added `pycln` configuration to `pyproject.toml`
+ * Added `alto2txt` as a command line script in `pyproject.toml`
 
 ### Changed
-* Switch from Apache v2.0 license to MIT license, inline with project recommendations.
+ * Switch from `Apache v2.0` license to `MIT` license, inline with project recommendations.
+ * Updated `mypy` in `.pre-commit-config.yaml`
 
 ### Deprecated
+ * Replace `extract_publications_text.py` with the `alto2txt` `command line interface` script specified in `pyproject.toml`
+
+### Removed
+ * `setup.py`
+ * `requirements.txt`
+
+### Fixed
+
+ * Fixed `python = ">3.6.0"` in `pyproject.toml` rather than `>3.7` for consistency with documentation
+ * Fixed licensing ambiguity (now all should be `MIT`)
+ * Fixed typos in `README.md`
+ * Fixed surperflous imports via `pycln` in `pre-commit`
+
+### Security
+
+## v0.3.3
+
+### Added
+
+### Changed
+
+### Deprecated
+
+### Removed
+
+### Fixed
+
+### Security
+
+## v0.3.2
+
+### Added
+
+### Changed
+
+### Deprecated
+
 ### Removed
+
 ### Fixed
+
 ### Security
 
+## v0.3.1
+
+### Added
+ * Added this changelog file.
+ * Established use of [Semantic Versioning](https://semver.org/spec/v2.0.0.html) for this project.
+ * Added a separate `CONTRIBUTING.md` doc for software developers notes.
+ * Added a separate copyright notice for example datasets
+
+### Changed
+
+### Deprecated
+
+### Removed
+
+### Fixed
+
+### Security
 
 ## v0.3.0 and before (prior to 2022-04-27)
 

LICENSE

@@ -1,7 +1,9 @@
-Copyright © 2022 The Alan Turing Institute, British Library Board, Queen Mary University of London, University of Exeter, University of East Anglia and University of Cambridge
+MIT License
 
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+Copyright (c) 2020 The Alan Turing Institute, British Library Board, Queen Mary University of London, University of Exeter, University of East Anglia and University of Cambridge
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 
 The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
 
-THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -1,6 +1,8 @@
-# Extract plain text from newspapers (alto2txt 0.3.1)
+# `alto2txt`: Extract plain text from newspapers
 
-Converts XML (in METS 1.8/ALTO 1.4, METS 1.3/ALTO 1.4, BLN or UKP format) publications to plaintext articles and generates minimal metadata.
+![GitHub](https://img.shields.io/github/license/Living-with-Machines/alto2txt) ![PyPI](https://img.shields.io/pypi/v/alto2txt)
+
+Converts `XML` (in `METS` `1.8`/`ALTO` `1.4`, `METS` `1.3`/`ALTO` `1.4`, `BLN` or `UKP` format) publications to plaintext articles and generates minimal metadata.
 
 
 ## [Full documentation and demo instructions.](https://living-with-machines.github.io/alto2txt/#/)
@@ -14,7 +16,7 @@ We recommend installation via Anaconda:
 
 * Refer to the [Anaconda website and follow the instructions](https://docs.anaconda.com/anaconda/install/).
 
-* Create a new environment for alto2txt
+* Create a new environment for `alto2txt`
 
 ```bash
 conda create -n py37alto python=3.7
@@ -26,19 +28,19 @@ conda create -n py37alto python=3.7
 conda activate py37alto
 ```
 
-* Install alto2txt itself
+* Install `alto2txt` itself
 
 Install `alto2txt` using pip:
 
 ```bash
 pip install alto2txt
 ```
 
-(For now it is still necessary to install using pip. In due course we plan to make alto2txt available through a conda channel, meaning that it can be installed directly using conda commands.)
+(For now it is still necessary to install using `pip`. In due course we plan to make `alto2txt` available through a `conda` channel, meaning that it can be installed directly using `conda` commands.)
 
 ### Installation using pip, outside an Anaconda environment
 
-Note, the use of `alto2txt`` outside a conda environment has not been as extensively tested as within a conda environment. Whilst we believe that this should work, please use with caution.
+Note, the use of ``alto2txt`` outside a conda environment has not been as extensively tested as within a conda environment. Whilst we believe that this should work, please use with caution.
 
 ```bash
 pip install alto2txt
@@ -54,16 +56,15 @@ pip install -i https://test.pypi.org/simple/ alto2txt==0.3.1a20
 
 ## Usage
 
-Downsampling can be used to convert only every Nth issue of each newspaper. One text file is output per article, each complemented by one XML metadata file.
+Downsampling can be used to convert only every Nth issue of each newspaper. One text file is output per article, each complemented by one `XML` metadata file.
 
 
 
 ```
-extract_publications_text.py [-h] [-d [DOWNSAMPLE]]
-                                    [-p [PROCESS_TYPE]]
-                                    [-l [LOG_FILE]]
-                                    [-n [NUM_CORES]]
-                                    xml_in_dir txt_out_dir
+usage: alto2txt [-h] [-p [PROCESS_TYPE]] [-l [LOG_FILE]] [-d [DOWNSAMPLE]] [-n [NUM_CORES]]
+                xml_in_dir txt_out_dir
+alto2txt [-h] [-p [PROCESS_TYPE]] [-l [LOG_FILE]] [-d [DOWNSAMPLE]] [-n [NUM_CORES]]
+         xml_in_dir txt_out_dir
 
 Converts XML publications to plaintext articles
 
@@ -73,19 +74,17 @@ positional arguments:
 
 optional arguments:
   -h, --help            show this help message and exit
-  -d [DOWNSAMPLE], --downsample [DOWNSAMPLE]
-                        Downsample. Default 1
+  -p [PROCESS_TYPE], --process-type [PROCESS_TYPE]
+                        Process type. One of: single,serial,multi,spark Default: multi
   -l [LOG_FILE], --log-file [LOG_FILE]
                         Log file. Default out.log
-  -p [PROCESS_TYPE], --process-type [PROCESS_TYPE]
-                        Process type.
-                        One of: single,serial,multi,spark
-                        Default: multi
+  -d [DOWNSAMPLE], --downsample [DOWNSAMPLE]
+                        Downsample. Default 1
   -n [NUM_CORES], --num-cores [NUM_CORES]
                         Number of cores (Spark only). Default 1")
 ```
 
-`xml_in_dir` is expected to hold XML for multiple publications, in the following structure:
+`xml_in_dir` is expected to hold `XML` for multiple publications, in the following structure:
 
 ```
 xml_in_dir
@@ -97,7 +96,7 @@ xml_in_dir
 |-- publication
 ```
 
-However, if `-p|--process-type single` is provided then `xml_in_dir` is expected to hold XML for a single publication, in the following structure:
+However, if `-p|--process-type single` is provided then `xml_in_dir` is expected to hold `XML` for a single publication, in the following structure:
 
 ```
 xml_in_dir
@@ -118,41 +117,41 @@ xml_in_dir
 
 `DOWNSAMPLE` must be a positive integer, default 1.
 
-The following XSLT files need to be in an `extract_text.xslts` module:
+The following `XSLT` files need to be in an `extract_text.xslts` module:
 
-* `extract_text_mets18.xslt`: METS 1.8 XSL file.
-* `extract_text_mets13.xslt`: METS 1.3 XSL file.
-* `extract_text_bln.xslt`: BLN XSL file.
-* `extract_text_ukp.xslt`: UKP XSL file.
+* `extract_text_mets18.xslt`: `METS 1.8 XSL` file.
+* `extract_text_mets13.xslt`: `METS 1.3 XSL` file.
+* `extract_text_bln.xslt`: `BLN XSL` file.
+* `extract_text_ukp.xslt`: `UKP XSL` file.
 
 ## Process publications
 
-Assume `~/BNA` exists and matches the structure above.
+Assume folder `BNA` exists and matches the structure above.
 
 Extract text from every publication:
 
 ```bash
-./extract_publications_text.py ~/BNA txt
+alto2txt BNA txt
 ```
 
 Extract text from every 100th issue of every publication:
 
 ```bash
-./extract_publications_text.py ~/BNA txt -d 100
+alto2txt BNA txt -d 100
 ```
 
 ## Process a single publication
 
 Extract text from every issue of a single publication:
 
 ```bash
-./extract_publications_text.py -p single ~/BNA/0000151 txt
+alto2txt -p single BNA/0000151 txt
 ```
 
 Extract text from every 100th issue of a single publication:
 
 ```bash
-./extract_publications_text.py -p single ~/BNA/0000151 txt -d 100
+alto2txt -p single BNA/0000151 txt -d 100
 ```
 
 ## Configure logging
@@ -162,7 +161,7 @@ By default, logs are put in `out.log`.
 To specify an alternative location for logs, use the `-l` flag e.g.
 
 ```bash
-./extract_publications_text.py -l mylog.txt ~/BNA txt -d 100 2> err.log
+alto2txt -l mylog.txt BNA txt -d 100 2> err.log
 ```
 
 ## Process publications via Spark