temporal-normalization-spacy 2.2.2__tar.gz → 2.3.0__tar.gz

{temporal_normalization_spacy-2.2.2 → temporal_normalization_spacy-2.3.0}/MANIFEST.in

@@ -1,5 +1,5 @@
 include README.md
-include temporal_normalization/libs/temporal-normalization-2.1.0.jar
+include temporal_normalization/libs/temporal-normalization-2.2.0.jar
 
 recursive-include temporal_normalizer/commons *
 recursive-include temporal_normalizer/libs *

{temporal_normalization_spacy-2.2.2/temporal_normalization_spacy.egg-info → temporal_normalization_spacy-2.3.0}/PKG-INFO

@@ -1,9 +1,10 @@
 Metadata-Version: 2.4
 Name: temporal_normalization_spacy
-Version: 2.2.2
+Version: 2.3.0
 Summary: A spaCy plugin for temporal normalization and extraction of historical dates in Romanian narrative texts.
 Home-page: https://github.com/iliedorobat/timespan-normalization-spacy
 Author: Ilie Cristian Dorobat
+Author-email: ic.dorobat@gmail.com
 Keywords: spacy,nlp,temporal normalization,timex,historical dates,romanian
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
@@ -19,6 +20,7 @@ Requires-Dist: spacy<4.0.0,>=3.8.7
 Requires-Dist: py4j>=0.10.9.9
 Requires-Dist: langdetect>=1.0.9
 Dynamic: author
+Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
@@ -78,12 +80,11 @@ quality and reliability of date-related information extracted from text.
 
 
 ## Getting started
-To integrate TeNs into spaCy pipelines you need the following:
 
 ### Prerequisites
 - Python 3.9-3.12
 - JRE 11-17
-- spaCy 3.x
+- spaCy >=3.8.7,<4.0.0
 - py4j 0.10.9.9
 - langdetect 1.0.9
 
@@ -233,24 +234,24 @@ Start Edge:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 
 End Edge:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 
 Periods:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 1st millennium BC
-	DBpedia uri: https://dbpedia.org/page/1st_millennium_BC
+	DBpedia uri: https://dbpedia.org/resource/1st_millennium_BC
 
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 ```
 
 ### Second Sentence
@@ -259,24 +260,24 @@ Start Edge:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 
 End Edge:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 
 Periods:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 2nd millennium
-	DBpedia uri: https://dbpedia.org/page/2nd_millennium
+	DBpedia uri: https://dbpedia.org/resource/2nd_millennium
 
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 ```
 
 ### Third Sentence
@@ -285,24 +286,24 @@ Start Edge:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 
 End Edge:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 
 Periods:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 3rd millennium
-	DBpedia uri: https://dbpedia.org/page/3rd_millennium
+	DBpedia uri: https://dbpedia.org/resource/3rd_millennium
 
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 ```
 
 

{temporal_normalization_spacy-2.2.2 → temporal_normalization_spacy-2.3.0}/README.md

@@ -47,12 +47,11 @@ quality and reliability of date-related information extracted from text.
 
 
 ## Getting started
-To integrate TeNs into spaCy pipelines you need the following:
 
 ### Prerequisites
 - Python 3.9-3.12
 - JRE 11-17
-- spaCy 3.x
+- spaCy >=3.8.7,<4.0.0
 - py4j 0.10.9.9
 - langdetect 1.0.9
 
@@ -202,24 +201,24 @@ Start Edge:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 
 End Edge:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 
 Periods:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 1st millennium BC
-	DBpedia uri: https://dbpedia.org/page/1st_millennium_BC
+	DBpedia uri: https://dbpedia.org/resource/1st_millennium_BC
 
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 ```
 
 ### Second Sentence
@@ -228,24 +227,24 @@ Start Edge:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 
 End Edge:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 
 Periods:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 2nd millennium
-	DBpedia uri: https://dbpedia.org/page/2nd_millennium
+	DBpedia uri: https://dbpedia.org/resource/2nd_millennium
 
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 ```
 
 ### Third Sentence
@@ -254,24 +253,24 @@ Start Edge:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 
 End Edge:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 
 Periods:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 3rd millennium
-	DBpedia uri: https://dbpedia.org/page/3rd_millennium
+	DBpedia uri: https://dbpedia.org/resource/3rd_millennium
 
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 ```
 
 

{temporal_normalization_spacy-2.2.2 → temporal_normalization_spacy-2.3.0}/setup.py

@@ -2,8 +2,9 @@ from setuptools import setup, find_packages
 
 setup(
     name="temporal_normalization_spacy",
-    version="2.2.2",
+    version="2.3.0",
     author="Ilie Cristian Dorobat",
+    author_email="ic.dorobat@gmail.com",
     description="A spaCy plugin for temporal normalization and extraction of "
     "historical dates in Romanian narrative texts.",
     keywords="spacy, nlp, temporal normalization, timex, historical dates, romanian",
@@ -18,7 +19,7 @@ setup(
         ],
     },
     package_data={
-        "temporal_normalization.libs": ["temporal-normalization-2.1.0.jar"],
+        "temporal_normalization.libs": ["temporal-normalization-2.2.0.jar"],
     },
     install_requires=[
         "spacy>=3.8.7,<4.0.0",

{temporal_normalization_spacy-2.2.2 → temporal_normalization_spacy-2.3.0}/temporal_normalization/index.py

@@ -43,6 +43,11 @@ class TemporalNormalization:
         self.nlp = nlp
         self.count = 0
 
+        # Initialize connection attributes before starting the Java gateway, as initialization may fail
+        # (e.g., during Flask's debug reloader), and __del__() may still be called on a partial instance.
+        self.java_process = None
+        self.gateway = None
+
         root_path = str(Path(__file__).resolve().parent.parent)
         java_process, gateway = start_conn(root_path)
         self.java_process: subprocess.Popen = java_process
@@ -97,7 +102,10 @@ class TemporalNormalization:
         network sockets that might otherwise persist after the Python process ends.
         """
 
-        close_conn(self.java_process, self.gateway)
+        if self.java_process is not None or self.gateway is not None:
+            close_conn(self.java_process, self.gateway)
+        else:
+            print(f"⚠️ No Java process or Python connection to close.")
 
 
 def _prepare_str_patterns(expressions: list[TemporalExpression]) -> list[str]:

temporal_normalization_spacy-2.3.0/temporal_normalization/process/java_process.py

@@ -0,0 +1,274 @@
+import io
+import re
+import shutil
+import subprocess
+import threading
+import time
+
+from py4j.java_gateway import JavaGateway, GatewayParameters
+from py4j.protocol import Py4JNetworkError
+
+from temporal_normalization.commons.print_utils import console
+
+
+def start_conn(root_path: str) -> tuple[subprocess.Popen, JavaGateway]:
+    """
+    Starts the Java temporal normalization process and establishes a Py4J gateway connection.
+
+    Args:
+        root_path (str): The root directory of the project.
+
+    Returns:
+        tuple[subprocess.Popen, JavaGateway]:
+            - The subprocess.Popen object representing the running Java process.
+            - The JavaGateway object representing the active Py4J connection.
+
+    Note:
+        - Requires Java 11 or higher to be installed and accessible in the system PATH.
+        - Requires `temporal-normalization-2.2.0.jar` to be present in the `libs` directory.
+        - The caller is responsible for closing the gateway and terminating the Java process
+            after usage to avoid orphaned processes.
+    """
+
+    check_java_version()
+
+    gateway_started = threading.Event()
+    gateway_error = threading.Event()
+
+    jar_path = (
+        f"{root_path}/temporal_normalization/libs/temporal-normalization-2.2.0.jar"
+    )
+
+    def stdout_callback(line: str):
+        if "Gateway Server Started" in line:
+            gateway_started.set()
+        print(line.strip())
+
+    stderr_lines = []
+    def stderr_callback(line: str):
+        stderr_lines.append(line)
+
+        if "Failed to bind" in line or "Address already in use" in line:
+            gateway_error.set()
+
+    java_process = subprocess.Popen(
+        ["java", "-jar", jar_path, "--python"],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+    )
+
+    threading.Thread(target=drain_stream, args=(java_process.stdout, stdout_callback), daemon=True).start()
+    threading.Thread(target=drain_stream, args=(java_process.stderr, stderr_callback), daemon=True).start()
+
+    timeout = 10.0
+    start_time = time.monotonic()
+
+    while not gateway_started.is_set():
+        if gateway_error.wait(timeout=0.1):
+            error = "\n\t".join(stderr_lines)
+
+            if java_process.poll() is None:
+                java_process.terminate()
+
+            raise RuntimeError(
+                "Java Gateway failed to start.\n"
+                f"Java stderr:\n\t{error}"
+            )
+
+        if time.monotonic() - start_time >= timeout:
+            error = "\n\t".join(stderr_lines)
+
+            java_process.terminate()
+            java_process.wait()
+
+            raise RuntimeError(
+                f"Java Gateway did not start within 10 seconds.\n"
+                f"Java stderr:\n\t{error}"
+            )
+
+        time.sleep(0.1)
+
+    gateway = JavaGateway(
+        gateway_parameters=GatewayParameters(auto_convert=True, read_timeout=None),
+        callback_server_parameters=None,
+    )
+
+    print("Python connection established.")
+
+    return java_process, gateway
+
+
+def close_conn(java_process: subprocess.Popen | None, gateway: JavaGateway | None) -> None:
+    """
+    Closes the Py4J gateway connection and terminates the associated Java process.
+
+    This function performs the shutdown sequence by:
+    1. Attempting to gracefully close the Py4J gateway connection.
+       - If the Java process has already terminated, the resulting
+         Py4JNetworkError is handled without raising an exception.
+    2. Terminating the Java process if it is still running.
+    3. Reporting the shutdown status for each resource.
+
+    Args:
+        java_process (subprocess.Popen | None): The Java process launched
+            with subprocess, or None if the process was not successfully
+            initialized.
+        gateway (JavaGateway | None): The active Py4J gateway connection,
+            or None if the gateway was not successfully initialized.
+
+    Notes:
+        - Call this function once all interactions with the Java process
+          have been completed.
+        - It is safe to call even if either the gateway or Java process
+          has already been closed or was not successfully initialized.
+        - The Py4J gateway is closed before the Java process is terminated.
+    """
+
+    _close_gateway_conn(gateway)
+    _close_java_conn(java_process)
+
+
+def _close_gateway_conn(gateway: JavaGateway | None) -> None:
+    """
+    Closes the active Py4J gateway connection, if one exists.
+
+    Attempts to gracefully shut down the connection between Python and
+    the Java process. If the Java process has already terminated, the
+    resulting Py4JNetworkError is handled and reported without raising
+    an exception.
+
+    Args:
+        gateway (JavaGateway | None): The active Py4J gateway connection,
+            or None if the connection was not successfully initialized.
+
+    Notes:
+        - It is safe to call this function when the gateway is None.
+        - It is safe to call this function after the Java process has
+          already terminated.
+        - Unexpected errors during gateway shutdown are caught and
+          reported rather than propagated.
+    """
+
+    if gateway is not None:
+        try:
+            # Proper way to shut down Py4J
+            gateway.shutdown()
+            print("✅ Python connection closed.")
+        except Py4JNetworkError:
+            print("⚠️ Java process already shut down.")
+        except Exception as e:
+            print(f"⚠️ Error shutting down gateway: {e}")
+    else:
+        print(f"⚠️ No Python connection to close.")
+
+
+def _close_java_conn(java_process: subprocess.Popen | None) -> None:
+    """
+    Terminates the Java process, if it is still running.
+
+    Checks whether the Java process is active before attempting to
+    terminate it. If the process has already exited, no termination
+    is attempted and a status message is printed.
+
+    Args:
+        java_process (subprocess.Popen | None): The Java process started
+            with subprocess, or None if the process was not successfully
+            initialized.
+
+    Notes:
+        - It is safe to call this function when java_process is None.
+        - It is safe to call this function after the Java process has
+          already terminated.
+        - If the process is still running, terminate() is called and the
+          function waits for the process to exit.
+    """
+
+    if java_process is None:
+        print("⚠️ No Java process to close.")
+        return
+
+    if java_process.poll() is None:
+        # Terminate Java process
+        java_process.terminate()
+        java_process.wait()
+        print("✅ Java process terminated.")
+    else:
+        print("⚠️ Java process already terminated.")
+
+
+def drain_stream(stream: io.TextIOBase, callback=None) -> None:
+    """
+    Consumes the output from a given stream until a specific marker is found,
+    then closes the stream.
+
+    This function is typically used to monitor the stdout or stderr of a subprocess
+    (e.g., a Java process started from Python) and detect when a certain event occurs,
+    such as the initialization of a gateway server. Once the marker line is encountered,
+    the function prints it (or logs it) and terminates the stream reading.
+
+    Args:
+        stream (io.TextIOBase): A text-based stream object to read from, usually
+                                subprocess.stdout or subprocess.stderr.
+        callback (callable, optional): A function that takes a single string argument (line).
+                                       It will be called for every line read from the stream.
+                                       Useful for detecting specific markers, logging, or
+                                       triggering events when certain output appears.
+
+    Raises:
+        AttributeError: If the provided `stream` does not have `readline` or `close` methods.
+    """
+
+    for line in iter(stream.readline, ""):
+        line = line.strip()
+        if callback:
+            callback(line)
+
+    stream.close()
+
+
+def check_java_version() -> None:
+    """
+    Verifies that Java is installed and meets the minimum required version.
+
+    This function checks for the presence of the Java executable in the system PATH,
+    runs ``java -version``, and ensures that the version is at least 11. If Java is not
+    installed or the version is too low, it logs an error using ``console.error``.
+
+    Raises:
+        Logs error messages, but does not raise exceptions directly.
+    """
+
+    min_version = 11
+    java_path = shutil.which("java")
+
+    try:
+        if java_path:
+            # Run the command to check the Java version
+            result = subprocess.run(
+                [java_path, "-version"], capture_output=True, text=True
+            )
+
+            # Print the version information (Java version is printed to stderr)
+            if result.returncode == 0:
+                version_output = result.stderr
+                match = re.search(r'version "(\d+\.\d+)', version_output)
+
+                if match:
+                    crr_version = float(match.group(1))
+                    if crr_version < min_version:
+                        console.error(
+                            f"Java {crr_version} is installed, but version {min_version} is required."  # noqa 501
+                        )
+                else:
+                    console.error("Could not extract Java version.")
+            else:
+                console.error("Error occurred while checking the version.")
+        else:
+            console.error("Java not found.")
+    except Exception as e:
+        console.error(e.__str__())
+
+
+if __name__ == "__main__":
+    pass

{temporal_normalization_spacy-2.2.2 → temporal_normalization_spacy-2.3.0/temporal_normalization_spacy.egg-info}/PKG-INFO

@@ -1,9 +1,10 @@
 Metadata-Version: 2.4
 Name: temporal_normalization_spacy
-Version: 2.2.2
+Version: 2.3.0
 Summary: A spaCy plugin for temporal normalization and extraction of historical dates in Romanian narrative texts.
 Home-page: https://github.com/iliedorobat/timespan-normalization-spacy
 Author: Ilie Cristian Dorobat
+Author-email: ic.dorobat@gmail.com
 Keywords: spacy,nlp,temporal normalization,timex,historical dates,romanian
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
@@ -19,6 +20,7 @@ Requires-Dist: spacy<4.0.0,>=3.8.7
 Requires-Dist: py4j>=0.10.9.9
 Requires-Dist: langdetect>=1.0.9
 Dynamic: author
+Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
@@ -78,12 +80,11 @@ quality and reliability of date-related information extracted from text.
 
 
 ## Getting started
-To integrate TeNs into spaCy pipelines you need the following:
 
 ### Prerequisites
 - Python 3.9-3.12
 - JRE 11-17
-- spaCy 3.x
+- spaCy >=3.8.7,<4.0.0
 - py4j 0.10.9.9
 - langdetect 1.0.9
 
@@ -233,24 +234,24 @@ Start Edge:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 
 End Edge:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 
 Periods:
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 1st millennium BC
-	DBpedia uri: https://dbpedia.org/page/1st_millennium_BC
+	DBpedia uri: https://dbpedia.org/resource/1st_millennium_BC
 
 	Matched value: Sec al II-lea a.ch.
 	Matched Type: century
 	Normalized label: 2nd century BC
-	DBpedia uri: https://dbpedia.org/page/2nd_century_BC
+	DBpedia uri: https://dbpedia.org/resource/2nd_century_BC
 ```
 
 ### Second Sentence
@@ -259,24 +260,24 @@ Start Edge:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 
 End Edge:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 
 Periods:
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 2nd millennium
-	DBpedia uri: https://dbpedia.org/page/2nd_millennium
+	DBpedia uri: https://dbpedia.org/resource/2nd_millennium
 
 	Matched value: secolul XX
 	Matched Type: century
 	Normalized label: 20th century
-	DBpedia uri: https://dbpedia.org/page/20th_century
+	DBpedia uri: https://dbpedia.org/resource/20th_century
 ```
 
 ### Third Sentence
@@ -285,24 +286,24 @@ Start Edge:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 
 End Edge:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 
 Periods:
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 3rd millennium
-	DBpedia uri: https://dbpedia.org/page/3rd_millennium
+	DBpedia uri: https://dbpedia.org/resource/3rd_millennium
 
 	Matched value: Sec. 21
 	Matched Type: century
 	Normalized label: 21st century
-	DBpedia uri: https://dbpedia.org/page/21st_century
+	DBpedia uri: https://dbpedia.org/resource/21st_century
 ```
 
 

{temporal_normalization_spacy-2.2.2 → temporal_normalization_spacy-2.3.0}/temporal_normalization_spacy.egg-info/SOURCES.txt

@@ -9,7 +9,7 @@ temporal_normalization/commons/__init__.py
 temporal_normalization/commons/print_utils.py
 temporal_normalization/commons/temporal_models.py
 temporal_normalization/commons/temporal_types.py
-temporal_normalization/libs/temporal-normalization-2.1.0.jar
+temporal_normalization/libs/temporal-normalization-2.2.0.jar
 temporal_normalization/process/__init__.py
 temporal_normalization/process/java_process.py
 temporal_normalization_spacy.egg-info/PKG-INFO

temporal_normalization_spacy-2.2.2/temporal_normalization/process/java_process.py

@@ -1,176 +0,0 @@
-import io
-import re
-import shutil
-import subprocess
-import threading
-
-from py4j.java_gateway import JavaGateway, GatewayParameters, CallbackServerParameters
-from py4j.protocol import Py4JNetworkError
-
-from temporal_normalization.commons.print_utils import console
-
-
-gateway_started = threading.Event()
-
-def start_conn(root_path: str) -> tuple[subprocess.Popen, JavaGateway]:
-    """
-    Starts the Java temporal normalization process and establishes a Py4J gateway connection.
-
-    Args:
-        root_path (str): The root directory of the project.
-
-    Returns:
-        tuple[subprocess.Popen, JavaGateway]:
-            - The subprocess.Popen object representing the running Java process.
-            - The JavaGateway object representing the active Py4J connection.
-
-    Note:
-        - Requires Java 11 or higher to be installed and accessible in the system PATH.
-        - Requires `temporal-normalization-2.1.0.jar` to be present in the `libs` directory.
-        - The caller is responsible for closing the gateway and terminating the Java process
-            after usage to avoid orphaned processes.
-    """
-
-    check_java_version()
-
-    jar_path = (
-        f"{root_path}/temporal_normalization/libs/temporal-normalization-2.1.0.jar"
-    )
-
-    def stdout_callback(line: str):
-        if "Gateway Server Started" in line:
-            gateway_started.set()
-        print(line.strip())
-
-    java_process = subprocess.Popen(
-        ["java", "-jar", jar_path, "--python"],
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-        text=True,
-    )
-
-    threading.Thread(target=drain_stream, args=(java_process.stdout, stdout_callback), daemon=True).start()
-    threading.Thread(target=drain_stream, args=(java_process.stderr,), daemon=True).start()
-
-    if not gateway_started.wait(timeout=10.0):
-        java_process.terminate()
-        raise RuntimeError("Java Gateway did not start within 10 seconds")
-
-    gateway = JavaGateway(
-        gateway_parameters=GatewayParameters(auto_convert=True, read_timeout=None),
-        callback_server_parameters=None,
-    )
-
-    print("Python connection established.")
-
-    return java_process, gateway
-
-
-def close_conn(java_process: subprocess.Popen, gateway: JavaGateway) -> None:
-    """
-    Closes the active connection between Python and the Java process started via Py4J.
-
-    This function ensures a proper shutdown sequence:
-    1. Attempts to gracefully shut down the Py4J gateway connection.
-       - If the Java process is already closed, a Py4JNetworkError is caught and logged.
-    2. Terminates the underlying Java process.
-    3. Prints status messages for debugging/confirmation.
-
-    Args:
-        java_process (subprocess.Popen): The Java process launched with subprocess.
-        gateway (JavaGateway): The active Py4J gateway connection.
-
-    Notes:
-        - Call this function once you have finished all interactions with the Java process.
-        - It is safe to call even if the Java process has already exited.
-    """
-
-    try:
-        # Proper way to shut down Py4J
-        gateway.shutdown()
-        print("✅ Python connection closed.")
-    except Py4JNetworkError:
-        print("⚠️ Java process already shut down.")
-    except Exception as e:
-        print(f"⚠️ Error shutting down gateway: {e}")
-
-    # Terminate Java process
-    java_process.terminate()
-    java_process.wait()
-    print("✅ Java process terminated.")
-
-
-def drain_stream(stream: io.TextIOBase, callback=None) -> None:
-    """
-    Consumes the output from a given stream until a specific marker is found,
-    then closes the stream.
-
-    This function is typically used to monitor the stdout or stderr of a subprocess
-    (e.g., a Java process started from Python) and detect when a certain event occurs,
-    such as the initialization of a gateway server. Once the marker line is encountered,
-    the function prints it (or logs it) and terminates the stream reading.
-
-    Args:
-        stream (io.TextIOBase): A text-based stream object to read from, usually
-                                subprocess.stdout or subprocess.stderr.
-        callback (callable, optional): A function that takes a single string argument (line).
-                                       It will be called for every line read from the stream.
-                                       Useful for detecting specific markers, logging, or
-                                       triggering events when certain output appears.
-
-    Raises:
-        AttributeError: If the provided `stream` does not have `readline` or `close` methods.
-    """
-    for line in iter(stream.readline, ""):
-        line = line.strip()
-        if callback:
-            callback(line)
-
-    stream.close()
-
-
-def check_java_version() -> None:
-    """
-    Verifies that Java is installed and meets the minimum required version.
-
-    This function checks for the presence of the Java executable in the system PATH,
-    runs ``java -version``, and ensures that the version is at least 11. If Java is not
-    installed or the version is too low, it logs an error using ``console.error``.
-
-    Raises:
-        Logs error messages, but does not raise exceptions directly.
-    """
-
-    min_version = 11
-    java_path = shutil.which("java")
-
-    try:
-        if java_path:
-            # Run the command to check the Java version
-            result = subprocess.run(
-                [java_path, "-version"], capture_output=True, text=True
-            )
-
-            # Print the version information (Java version is printed to stderr)
-            if result.returncode == 0:
-                version_output = result.stderr
-                match = re.search(r'version "(\d+\.\d+)', version_output)
-
-                if match:
-                    crr_version = float(match.group(1))
-                    if crr_version < min_version:
-                        console.error(
-                            f"Java {crr_version} is installed, but version {min_version} is required."  # noqa 501
-                        )
-                else:
-                    console.error("Could not extract Java version.")
-            else:
-                console.error("Error occurred while checking the version.")
-        else:
-            console.error("Java not found.")
-    except Exception as e:
-        console.error(e.__str__())
-
-
-if __name__ == "__main__":
-    pass