Merge branch 'master' into flavor

.github/workflows/ci-build.yml

@@ -0,0 +1,39 @@
+name: Build unstable
+
+on: [push]
+
+concurrency: 
+  group: unstable
+
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ '3.8', '3.9', '3.10', '3.11', '3.12', '3.13' ]
+      fail-fast: true
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+      - name: Cleanup more disk space
+        run: sudo rm -rf /usr/share/dotnet && sudo rm -rf /opt/ghc && sudo rm -rf "/usr/local/share/boost" && sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --upgrade flake8 pytest pycodestyle pytest-cov
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Lint with flake8
+        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=127 --statistics
+#      - name: Test with pytest
+#        run: |
+#          pytest

.github/workflows/ci-release.yml

@@ -0,0 +1,43 @@
+name: Build release
+
+on:
+  workflow_dispatch:
+  push:
+    tags:
+      - 'v*'
+
+concurrency:
+  group: docker
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+          cache: 'pip'
+      - name: Cleanup more disk space
+        run: sudo rm -rf /usr/share/dotnet && sudo rm -rf /opt/ghc && sudo rm -rf "/usr/local/share/boost" && sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --upgrade flake8 pytest pycodestyle
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Lint with flake8
+        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=127 --statistics
+    #    - name: Test with pytest
+    #      run: |
+    #        pytest
+
+      - name: Build and Publish to PyPI
+        uses: conchylicultor/pypi-build-publish@v1
+        with:
+          pypi-token: ${{ secrets.PYPI_API_TOKEN }}

Readme.md

@@ -20,14 +20,31 @@ You can change the server address by editing the file `config.json`, see below.
 
 ## Requirements
 
-This client has been developed and was tested with Python `3.5`-`3.9` and should work with any higher `3.*` versions. It uses `requests` as dependency beyond the Standard Python Library.
+This client has been developed and was tested with Python `3.8`-`3.13` and should work with any higher `3.*` versions. 
+It uses `requests` as dependency beyond the Standard Python Library.
 
 ## Install
 
-Get the github repo:
+The client can be installed with any of the following ways:
+
+* Install *latest stable release* from PyPI:
+
+```console
+python3 -m pip install grobid-client-python
+```
+
+* Install *current master development version* from GitHub:
 
 ```console
-pip install git+https://github.com/kermitt2/grobid_client_python.git
+python3 -m pip install git+https://github.com/kermitt2/grobid_client_python.git
+```
+
+* Install and build from a clone of the repo (*current master development version*): 
+
+```
+git clone https://github.com/kermitt2/grobid_client_python
+cd grobid_client_python
+pip install -e . 
 ```
 
 There is nothing more needed to start using the python command lines, see the next section. 
@@ -177,6 +194,20 @@ In similar conditions, extraction and structuring of bibliographical references
 Processing of 3500 raw bibliographical take 4.3 s with `n=10` (814 references parsed per second).
 
 
+## Developer notes 
+
+### New release 
+
+New releases can be published by using `bump-my-version`:
+
+```shell
+pip install bump-my-version
+bump-my-version bump patch 
+```
+
+Use of  `major`, `minor`, or `patch` or  will increment the first, second or the third digit of the version, respectively.  
+The release will be published automatically on pypy. 
+
 ## License and contact
 
 Distributed under [Apache 2.0 license](http://www.apache.org/licenses/LICENSE-2.0). 

grobid_client/grobid_client.py

@@ -261,6 +261,8 @@ def process_pdf(
         include_raw_affiliations,
         tei_coordinates,
         segment_sentences,
+        start=-1,
+        end=-1,
         flavor=None
     ):
         pdf_handle = open(pdf_file, "rb")
@@ -293,6 +295,10 @@ def process_pdf(
             the_data["segmentSentences"] = "1"
         if flavor:
             the_data["flavor"] = flavor
+        if start > 0:
+            the_data["start"] = str(start)
+        if end > 0:
+            the_data["end"] = str(end)
 
         try:
             res, status = self.post(
@@ -310,7 +316,9 @@ def process_pdf(
                     include_raw_citations,
                     include_raw_affiliations,
                     tei_coordinates,
-                    segment_sentences
+                    segment_sentences,
+                    start,
+                    end
                 )
         except requests.exceptions.ReadTimeout:
             pdf_handle.close()

pyproject.toml

@@ -0,0 +1,40 @@
+[build-system]
+requires = ["setuptools", "setuptools-scm"]
+build-backend = "setuptools.build_meta"
+
+[tool.bumpversion]
+current_version = "0.0.9"
+commit = "true"
+tag = "true"
+tag_name = "v{new_version}"
+
+[project]
+name = "grobid-client-python"
+license = { file = "LICENSE" }
+authors = [
+    { name = "Patrice Lopez", email = "[email protected]" },
+]
+maintainers = [
+    { name = "Patrice Lopez", email = "[email protected]" },
+    { name = "Luca Foppiano", email = "[email protected]" }
+]
+description = "Simple python client for GROBID REST services"
+readme = "Readme.md"
+
+dynamic = ['version', "dependencies"]
+
+[tool.setuptools.dynamic]
+dependencies = {file = ["requirements.txt"]}
+
+[tool.setuptools_scm]
+
+[tool.setuptools]
+packages=['grobid_client']
+
+[project.urls]
+Homepage = "https://github.com/kermitt2/grobid_client_python"
+Repository = "https://github.com/kermitt2/grobid_client_python"
+Changelog = "https://github.com/kermitt2/grobid_client_python"
+
+[project.scripts]
+grobid_client = "grobid_client.grobid_client:main"

requirements.txt

@@ -0,0 +1 @@
+requests