Merge pull request #80 from weblyzard/feature/python3.12

Feature/python3.12

.git-blame-ignore-revs

@@ -0,0 +1 @@
+55fa29ca39f9ed5895f9e88b2eb0f17e4d84245f

.github/workflows/codeql-analysis.yml

@@ -13,10 +13,7 @@ name: "CodeQL"
 
 on:
   push:
-    branches: [ master ]
   pull_request:
-    # The branches below must be a subset of the branches above
-    branches: [ master ]
   schedule:
     - cron: '26 5 * * 2'
 

.github/workflows/python-package.yml

@@ -2,37 +2,27 @@ name: build
 
 on:
   push:
-    branches: [ master ]
   pull_request:
-    branches: [ master ]
 
 jobs:
   build:
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.6', '3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: [ '3.8', '3.9', '3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
+    - name: Install build environment
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest pytest-cov codecov
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-        python setup.py install
-    - name: Lint with flake8
+        python -m pip install tox setuptools pytest pytest-cov codecov
+    - name: Build and test with tox.
       run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=80 --statistics
-    - name: Test with pytest
-      run: |
-        py.test --cov=inscripits ./tests && codecov
+        tox

.gitignore

@@ -23,3 +23,4 @@ tests/reference.txt
 *.c
 docs/paper/*.pdf
 htmlcov/
+poetry.lock

Dockerfile

@@ -4,10 +4,8 @@
 FROM python:3.11-slim-bullseye AS builder
 
 WORKDIR /inscriptis
-COPY requirements.txt .
 RUN python -m venv .venv && .venv/bin/python -m pip install --upgrade pip
-RUN .venv/bin/pip install --no-cache-dir -r requirements.txt && \
-    .venv/bin/pip install --no-cache-dir Flask waitress && \
+RUN .venv/bin/pip install --no-cache-dir inscriptis[web-service] && \
     find /inscriptis/.venv \( -type d -a -name test -o -name tests \) -o \( -type f -a -name '*.pyc' -o -name '*.pyo' \) -exec rm -rf '{}' \+
 
 #
@@ -18,10 +16,9 @@ LABEL maintainer="[email protected]"
 
 # Note: only copy the src directory, to prevent bloating the image with 
 #       irrelevant files from the project directory.
-WORKDIR /inscriptis/src
+WORKDIR /inscriptis
 COPY --from=builder /inscriptis /inscriptis
-COPY ./src /inscriptis/src
 
 ENV PATH="/inscriptis/.venv/bin:$PATH"
-CMD ["waitress-serve", "inscriptis.service.web:app", "--port=5000", "--host=0.0.0.0"]
+CMD ["uvicorn", "inscriptis.service.web:app", "--port=5000", "--host=0.0.0.0"]
 EXPOSE 5000

README.rst

@@ -131,9 +131,9 @@ the corresponding text representation.
 Command line parameters
 -----------------------
 
-The inscript.py command line client supports the following parameters::
+The inscript command line client supports the following parameters::
 
-    usage: inscript.py [-h] [-o OUTPUT] [-e ENCODING] [-i] [-d] [-l] [-a] [-r ANNOTATION_RULES] [-p POSTPROCESSOR] [--indentation INDENTATION]
+    usage: inscript [-h] [-o OUTPUT] [-e ENCODING] [-i] [-d] [-l] [-a] [-r ANNOTATION_RULES] [-p POSTPROCESSOR] [--indentation INDENTATION]
                        [--table-cell-separator TABLE_CELL_SEPARATOR] [-v]
                        [input]
 
@@ -172,19 +172,19 @@ HTML to text conversion
 -----------------------
 convert the given page to text and output the result to the screen::
 
-  $ inscript.py https://www.fhgr.ch
+  $ inscript https://www.fhgr.ch
    
 convert the file to text and save the output to fhgr.txt::
 
-  $ inscript.py fhgr.html -o fhgr.txt
+  $ inscript fhgr.html -o fhgr.txt
 
 convert the file using strict indentation (i.e., minimize indentation and extra spaces) and save the output to fhgr-layout-optimized.txt::
 
-  $ inscript.py --indentation strict fhgr.html -o fhgr-layout-optimized.txt
+  $ inscript --indentation strict fhgr.html -o fhgr-layout-optimized.txt
    
 convert HTML provided via stdin and save the output to output.txt::
 
-  $ echo "<body><p>Make it so!</p></body>" | inscript.py -o output.txt 
+  $ echo "<body><p>Make it so!</p></body>" | inscript -o output.txt 
 
 
 HTML to annotated text conversion
@@ -193,7 +193,7 @@ convert and annotate HTML from a Web page using the provided annotation rules.
 
 Download the example `annotation-profile.json <https://github.com/weblyzard/inscriptis/blob/master/examples/annotation-profile.json>`_ and save it to your working directory::
 
-  $ inscript.py https://www.fhgr.ch -r annotation-profile.json
+  $ inscript https://www.fhgr.ch -r annotation-profile.json
 
 The annotation rules are specified in `annotation-profile.json`:
 
@@ -241,7 +241,7 @@ Annotation postprocessors enable the post processing of annotations to formats
 that are suitable for your particular application. Post processors can be
 specified with the ``-p`` or ``--postprocessor`` command line argument::
 
-  $ inscript.py https://www.fhgr.ch \
+  $ inscript https://www.fhgr.ch \
           -r ./examples/annotation-profile.json \
           -p surface
 
@@ -286,7 +286,7 @@ Currently, inscriptis supports the following postprocessors:
 
    .. code-block:: bash
 
-      inscript.py --annotation-rules ./wikipedia.json \
+      inscript --annotation-rules ./wikipedia.json \
                   --postprocessor html \
                   https://en.wikipedia.org/wiki/Chur.html
 
@@ -311,14 +311,18 @@ Currently, inscriptis supports the following postprocessors:
 Web Service
 ===========
 
-The Flask Web Service translates HTML pages to the corresponding plain text.
+A FastAPI-based Web Service that uses Inscriptis for translating HTML pages to plain text.
 
 Run the Web Service on your host system
 ---------------------------------------
-Provide additional requirement `python3-flask <https://flask.palletsprojects.com/en/2.2.x/>`_, then start the inscriptis Web service with the following command::
+Install the optional feature `web-service` for inscriptis::
+  
+  $ pip install inscriptis[web-service]
+
+Start the Inscriptis Web service with the following command::
+
+  $ uvicorn inscriptis.service.web:app --port 5000 --host 127.0.0.1
 
-  $ export FLASK_APP="inscriptis.service.web"
-  $ python3 -m flask run
 
 Run the Web Service with Docker
 -------------------------------
@@ -499,7 +503,7 @@ The following options are available for fine tuning inscriptis' HTML rendering:
 1. **More rigorous indentation:** call ``inscriptis.get_text()`` with the
    parameter ``indentation='extended'`` to also use indentation for tags such as
    ``<div>`` and ``<span>`` that do not provide indentation in their standard
-   definition. This strategy is the default in ``inscript.py`` and many other
+   definition. This strategy is the default in ``inscript`` and many other
    tools such as Lynx. If you do not want extended indentation you can use the
    parameter ``indentation='standard'`` instead.