Dev

.github/workflows/pypi-publish.yml

@@ -0,0 +1,84 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+# GitHub recommends pinning actions to a commit SHA.
+# To get a newer version, you will need to update the SHA.
+# You can also reference a tag or branch, but the action may change without warning.
+
+name: Upload on Pypi
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pytest
+          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 unittest
+        run: |
+          python3 -m unittest tests/tests.py 
+
+  release-build:
+    needs: build-and-test
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v5
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Build release distributions
+        run: |
+          # NOTE: put your own distribution build steps here.
+          python -m pip install build
+          python -m build
+
+      - name: Upload distributions
+        uses: actions/upload-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+  pypi-publish:
+    needs: release-build
+    name: Publish package distributions to TestPyPI
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://pypi.org/project/corpus-query-language
+    permissions:
+      id-token: write  # IMPORTANT: this permission is mandatory for trusted publishing
+    steps:
+      - name: Télécharger les artefacts du build
+        uses: actions/download-artifact@v4  # <-- Ajoutez cette étape
+        with:
+          name: release-dists  # <-- Nom de l'artefact uploadé dans `release-build`
+          path: dist/
+      # retrieve your distributions here
+      - name: Publish package distributions to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://upload.pypi.org/legacy/

.github/workflows/python-app.yml → .github/workflows/test.yml

@@ -4,17 +4,14 @@
 name: Python application
 
 on:
-  push:
-    branches: [ "main", "dev" ]
   pull_request:
-    branches: [ "main" ]
+    branches: [ "main", "dev" ]
 
 permissions:
   contents: read
 
 jobs:
-  build:
-
+  Test-code:
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/testpypi-publish.yml

@@ -7,7 +7,7 @@
 # To get a newer version, you will need to update the SHA.
 # You can also reference a tag or branch, but the action may change without warning.
 
-name: Upload Python Package
+name: Upload on test.pypi
 
 on:
   push:
@@ -17,7 +17,31 @@ permissions:
   contents: read
 
 jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pytest
+          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 unittest
+        run: |
+          python3 -m unittest tests/tests.py 
+
   release-build:
+    needs: build-and-test
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v5
@@ -44,7 +68,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: testpypi
-      url: https://test.pypi.org/p/CQLEngine
+      url: https://test.pypi.org/p/corpus-query-language
     permissions:
       id-token: write  # IMPORTANT: this permission is mandatory for trusted publishing
     steps:
@@ -57,4 +81,4 @@ jobs:
       - name: Publish package distributions to TestPyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
-          repository-url: https://test.pypi.org/p/CQLEngine
+          repository-url: https://test.pypi.org/legacy/

CQL.py

@@ -0,0 +1,26 @@
+# Python package project: CQL (Corpus Query Language) parser:
+# - parsing of any kind of annotation: word, lemma, pos, morph
+# - combination of annotations: [lemma='rey' & pos='NCMP000']
+# - one or zero annotations [lemma='rey']?.
+# - distance [lemma='rey'][]{,5}[lemma='santo']
+# - any regex in the annotation value [lemma='reye?s?']
+# - alternatives: [lemma='rey']|[lemma='príncipe'][]{,5}[lemma='santo']
+import sys
+import CQLEngine.functions as functions
+
+# Takes a list of dicts with the annotations as input. Returns:
+# - a list of spans (search_all function)
+# - a boolean (match function)
+
+
+
+def main():
+	query = sys.argv[1]
+	corpus = functions.import_corpus("tests/test_data/test_corpus.json")
+	MyEngine = functions.CQLEngine()
+	MyEngine.findall(corpus, query)
+	MyEngine.match(corpus, query)
+
+
+if __name__ == '__main__':
+	main()

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "CQLEngine"
+name = "corpus-query-language"
 version = "0.0.1"
 authors = [
   { name="Matthias Gille Levenson", email="matthias.gille-levenson@ens-lyon.fr" },
@@ -13,6 +13,13 @@ classifiers = [
 ]
 license = " CC-BY-NC-SA-4.0"
 license-files = ["LICEN[CS]E*"]
+dependencies = [
+    "ply"
+]
+
+[build-system]
+requires = ["setuptools", "setuptools-scm"]
+build-backend = "setuptools.build_meta"
 
 [project.urls]
 Homepage = "https://github.com/matgille/CQL"

src/CQLEngine/engine.py

@@ -1,7 +1,9 @@
-import src.CQLEngine.functions as functions
+import CQLEngine.functions as functions
 
-def parse_corpus(ast, corpus, debug, match=True):
+
+def parse_corpus(ast, corpus, mode, debug):
 	match = False
+	text_end = False
 	tree_index = 0
 	text_index = 0
 
@@ -20,45 +22,49 @@ def parse_corpus(ast, corpus, debug, match=True):
 	analysis_list = ['lemma', 'pos', 'morph', 'word']
 
 	# Text-directed engine.
-	while match == False:
-		if debug:
-			print("-")
-			print(corpus[text_index])
-			print(f"Text index: {text_index}")
-			print(f"Tree index: {tree_index}")
-			print(f"Ast length: {ast_length}")
+	while text_end == False:
 
 		# On teste si on est en bout de texte.
-		if len(corpus) == text_index:
-			if debug:
-				print("End of text. Exiting.")
-			break
-		if text_index + 1 == len(corpus):
-			tree_index += 1
+		if len(corpus) == text_index and tree_index != ast_length:
 			if debug:
-				print("End of text. Exiting.")
+				print("End of text a. Exiting.")
+			text_end = True
+			if mode == "match":
+				return False
 			break
+
+
 		# Si on matche la longueur de notre arbre
 		if tree_index == ast_length:
+			match = True
 			all_spans.append((first_matching_index, text_index))
-			first_matching_index = None
-			if match is True:
-				return True
 			if debug:
 				print(f"Appending {(first_matching_index, text_index)} to spans.")
 				print(tree_index)
 				print(ast_length)
+			first_matching_index = None
+			if match is True and mode == "match":
+				return True
 			text_index += 1
 			tree_index = 0
 			matches = True
 			# La boucle s'arrête là
+
+		if debug:
+			print("-")
+			print(corpus[text_index])
+			print(f"Text index: {text_index}")
+			print(f"Tree index: {tree_index}")
+			print(f"Ast length: {ast_length}")
 		current_query = ast[tree_index]
 		operator = current_query[0]
 		if debug:
 			print(f"Current query: {current_query}")
 		if operator in analysis_list:
 			if debug:
 				print(f"{operator} in list of analysis")
+				print(len(corpus))
+				print(text_index)
 			if functions.simple_match(current_query, corpus[text_index]):
 				if debug:
 					print("Found you a. Going forward on tree and text.")