grobid-client-python 0.1.3__tar.gz → 0.1.5__tar.gz

grobid_client_python-0.1.5/.github/dependabot.yml

@@ -0,0 +1,9 @@
+version: 2
+updates:
+  # Keep GitHub Actions used in the workflows up to date
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    commit-message:
+      prefix: "ci"

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/.github/workflows/ci-build.yml

@@ -15,9 +15,9 @@ jobs:
       fail-fast: true
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v7
         with:
           python-version: ${{ matrix.python-version }}
           cache: 'pip'
@@ -43,7 +43,7 @@ jobs:
           pytest tests/ -v --cov=grobid_client --cov-report=xml --cov-report=term-missing
       - name: Upload coverage to Codecov
         if: matrix.python-version == '3.11'
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v7
         with:
           file: ./coverage.xml
           flags: unittests

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/.github/workflows/ci-release.yml

@@ -14,9 +14,9 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
       - name: Set up Python 3.9
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v7
         with:
           python-version: "3.9"
           cache: 'pip'

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: grobid-client-python
-Version: 0.1.3
+Version: 0.1.5
 Summary: Simple python client for GROBID REST services
 Author-email: Patrice Lopez <patrice.lopez@science-miner.com>
 Maintainer-email: Patrice Lopez <patrice.lopez@science-miner.com>, Luca Foppiano <lucanoro@duck.com>
@@ -353,13 +353,13 @@ grobid_client [OPTIONS] SERVICE
 
 | Option                       | Description                               |
 |------------------------------|-------------------------------------------|
-| `--generateIDs`              | Generate random XML IDs                   |
+| `--generate_ids`             | Generate random XML IDs                   |
 | `--consolidate_header`       | Consolidate header metadata               |
 | `--consolidate_citations`    | Consolidate bibliographic references      |
 | `--include_raw_citations`    | Include raw citation text                 |
 | `--include_raw_affiliations` | Include raw affiliation text              |
-| `--teiCoordinates`           | Add PDF coordinates to XML                |
-| `--segmentSentences`         | Segment sentences with coordinates        |
+| `--tei_coordinates`          | Add PDF coordinates to XML                |
+| `--segment_sentences`        | Segment sentences with coordinates        |
 | `--flavor`                   | Processing flavor for fulltext extraction |
 | `--json`                     | Convert TEI output to JSON format         |
 | `--markdown`                 | Convert TEI output to Markdown format     |
@@ -372,7 +372,7 @@ grobid_client [OPTIONS] SERVICE
 grobid_client --input ~/documents --output ~/results processFulltextDocument
 
 # High concurrency with coordinates
-grobid_client --input ~/pdfs --output ~/tei --n 20 --teiCoordinates processFulltextDocument
+grobid_client --input ~/pdfs --output ~/tei --n 20 --tei_coordinates processFulltextDocument
 
 # Process with JSON output
 grobid_client --input ~/pdfs --output ~/results --json processFulltextDocument
@@ -384,7 +384,7 @@ grobid_client --input ~/pdfs --output ~/results --markdown processFulltextDocume
 grobid_client --server https://grobid.example.com --input ~/citations.txt processCitationList
 
 # Force reprocessing with sentence segmentation and JSON output
-grobid_client --input ~/docs --force --segmentSentences --json processFulltextDocument
+grobid_client --input ~/docs --force --segment_sentences --json processFulltextDocument
 ```
 
 ### Python Library
@@ -421,10 +421,10 @@ client.process(
     input_path="/path/to/pdfs",
     output_path="/path/to/output",
     n=10,
-    generateIDs=True,
+    generate_ids=True,
     consolidate_header=True,
-    teiCoordinates=True,
-    segmentSentences=True
+    tei_coordinates=True,
+    segment_sentences=True
 )
 
 # Process with JSON output
@@ -517,6 +517,14 @@ settings.
 > Since version 0.0.12, the config file is optional. The client will use default localhost settings if no configuration
 > is provided.
 
+> [!WARNING]
+> **Citation consolidation and the `timeout` setting.** When `--consolidate_citations` (or `consolidate_citations=True`)
+> is enabled, GROBID queries external services (e.g. CrossRef) to enrich the extracted references. This is considerably
+> slower than a plain extraction, and a low `timeout` frequently causes `HTTP 408 (Request Timeout)` errors.
+> Set the `timeout` to at least **120 seconds (2-3 minutes recommended)** when consolidating citations. The client emits
+> a warning when consolidation is requested with a timeout below 120 seconds.
+> See [issue #54](https://github.com/grobidOrg/grobid-client-python/issues/54).
+
 ### Logging Configuration
 
 The client provides configurable logging with different verbosity levels. By default, only essential statistics and warnings are shown.
@@ -673,7 +681,7 @@ When using the `--json` flag, the client converts TEI XML output to a structured
 grobid_client --input pdfs/ --output results/ --json processFulltextDocument
 
 # JSON output with coordinates and sentence segmentation
-grobid_client --input pdfs/ --output results/ --json --teiCoordinates --segmentSentences processFulltextDocument
+grobid_client --input pdfs/ --output results/ --json --tei_coordinates --segment_sentences processFulltextDocument
 ```
 
 ```python
@@ -754,7 +762,7 @@ Competing interests statement...
 grobid_client --input pdfs/ --output results/ --markdown processFulltextDocument
 
 # Markdown output with coordinates and sentence segmentation
-grobid_client --input pdfs/ --output results/ --markdown --teiCoordinates --segmentSentences processFulltextDocument
+grobid_client --input pdfs/ --output results/ --markdown --tei_coordinates --segment_sentences processFulltextDocument
 ```
 
 ```python

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/Readme.md

@@ -134,13 +134,13 @@ grobid_client [OPTIONS] SERVICE
 
 | Option                       | Description                               |
 |------------------------------|-------------------------------------------|
-| `--generateIDs`              | Generate random XML IDs                   |
+| `--generate_ids`             | Generate random XML IDs                   |
 | `--consolidate_header`       | Consolidate header metadata               |
 | `--consolidate_citations`    | Consolidate bibliographic references      |
 | `--include_raw_citations`    | Include raw citation text                 |
 | `--include_raw_affiliations` | Include raw affiliation text              |
-| `--teiCoordinates`           | Add PDF coordinates to XML                |
-| `--segmentSentences`         | Segment sentences with coordinates        |
+| `--tei_coordinates`          | Add PDF coordinates to XML                |
+| `--segment_sentences`        | Segment sentences with coordinates        |
 | `--flavor`                   | Processing flavor for fulltext extraction |
 | `--json`                     | Convert TEI output to JSON format         |
 | `--markdown`                 | Convert TEI output to Markdown format     |
@@ -153,7 +153,7 @@ grobid_client [OPTIONS] SERVICE
 grobid_client --input ~/documents --output ~/results processFulltextDocument
 
 # High concurrency with coordinates
-grobid_client --input ~/pdfs --output ~/tei --n 20 --teiCoordinates processFulltextDocument
+grobid_client --input ~/pdfs --output ~/tei --n 20 --tei_coordinates processFulltextDocument
 
 # Process with JSON output
 grobid_client --input ~/pdfs --output ~/results --json processFulltextDocument
@@ -165,7 +165,7 @@ grobid_client --input ~/pdfs --output ~/results --markdown processFulltextDocume
 grobid_client --server https://grobid.example.com --input ~/citations.txt processCitationList
 
 # Force reprocessing with sentence segmentation and JSON output
-grobid_client --input ~/docs --force --segmentSentences --json processFulltextDocument
+grobid_client --input ~/docs --force --segment_sentences --json processFulltextDocument
 ```
 
 ### Python Library
@@ -202,10 +202,10 @@ client.process(
     input_path="/path/to/pdfs",
     output_path="/path/to/output",
     n=10,
-    generateIDs=True,
+    generate_ids=True,
     consolidate_header=True,
-    teiCoordinates=True,
-    segmentSentences=True
+    tei_coordinates=True,
+    segment_sentences=True
 )
 
 # Process with JSON output
@@ -298,6 +298,14 @@ settings.
 > Since version 0.0.12, the config file is optional. The client will use default localhost settings if no configuration
 > is provided.
 
+> [!WARNING]
+> **Citation consolidation and the `timeout` setting.** When `--consolidate_citations` (or `consolidate_citations=True`)
+> is enabled, GROBID queries external services (e.g. CrossRef) to enrich the extracted references. This is considerably
+> slower than a plain extraction, and a low `timeout` frequently causes `HTTP 408 (Request Timeout)` errors.
+> Set the `timeout` to at least **120 seconds (2-3 minutes recommended)** when consolidating citations. The client emits
+> a warning when consolidation is requested with a timeout below 120 seconds.
+> See [issue #54](https://github.com/grobidOrg/grobid-client-python/issues/54).
+
 ### Logging Configuration
 
 The client provides configurable logging with different verbosity levels. By default, only essential statistics and warnings are shown.
@@ -454,7 +462,7 @@ When using the `--json` flag, the client converts TEI XML output to a structured
 grobid_client --input pdfs/ --output results/ --json processFulltextDocument
 
 # JSON output with coordinates and sentence segmentation
-grobid_client --input pdfs/ --output results/ --json --teiCoordinates --segmentSentences processFulltextDocument
+grobid_client --input pdfs/ --output results/ --json --tei_coordinates --segment_sentences processFulltextDocument
 ```
 
 ```python
@@ -535,7 +543,7 @@ Competing interests statement...
 grobid_client --input pdfs/ --output results/ --markdown processFulltextDocument
 
 # Markdown output with coordinates and sentence segmentation
-grobid_client --input pdfs/ --output results/ --markdown --teiCoordinates --segmentSentences processFulltextDocument
+grobid_client --input pdfs/ --output results/ --markdown --tei_coordinates --segment_sentences processFulltextDocument
 ```
 
 ```python

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/grobid_client/format/TEI2LossyJSON.py

@@ -875,8 +875,6 @@ def get_refs_with_offsets(element):
     def _clean_text(text: str) -> str:
         if not text:
             return ""
-        import re
-        import html
         text = re.sub(r'\s+', ' ', text.strip())
         text = html.unescape(text)
         return text
@@ -961,8 +959,6 @@ def get_formatted_passage(head_paragraph, head_section, paragraph_id, element):
     def _clean_text_local(text: str) -> str:
         if not text:
             return ""
-        import re
-        import html
         text = re.sub(r'\s+', ' ', text.strip())
         text = html.unescape(text)
         return text

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/grobid_client/format/TEI2Markdown.py

@@ -648,8 +648,6 @@ class TEI2MarkdownConverter:
 
     def _extract_year(self, date_text: str) -> str:
         """Extract year from date text, handling various formats."""
-        import re
-
         # Look for 4-digit year patterns
         year_match = re.search(r'\b(19|20)\d{2}\b', date_text)
         if year_match:

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/grobid_client/grobid_client.py

@@ -20,6 +20,7 @@ import argparse
 import time
 import concurrent.futures
 import ntpath
+import re
 import requests
 import pathlib
 import logging
@@ -39,6 +40,11 @@ class ServerUnavailableException(Exception):
 
 
 class GrobidClient(ApiClient):
+    # Below this client-side timeout (in seconds) citation consolidation is
+    # likely to trigger HTTP 408 (Request Timeout) errors, so we warn the user.
+    # See https://github.com/grobidOrg/grobid-client-python/issues/54
+    CONSOLIDATE_CITATIONS_MIN_TIMEOUT = 120
+
     # Default configuration values
     DEFAULT_CONFIG = {
         'grobid_server': 'http://localhost:8070',
@@ -112,6 +118,27 @@ class GrobidClient(ApiClient):
             if value is not None:
                 self.config[key] = value
 
+    def _warn_on_consolidation_timeout(self, consolidate_citations):
+        """Warn when citation consolidation is enabled with a low client timeout.
+
+        Consolidating citations makes GROBID query external services and can be
+        much slower than a plain extraction. A short client-side timeout often
+        leads to HTTP 408 errors, so we recommend at least a couple of minutes.
+        See https://github.com/grobidOrg/grobid-client-python/issues/54
+        """
+        if not consolidate_citations:
+            return
+
+        timeout = self.config.get("timeout", self.DEFAULT_CONFIG["timeout"])
+        if timeout < self.CONSOLIDATE_CITATIONS_MIN_TIMEOUT:
+            self.logger.warning(
+                f"Citation consolidation is enabled but the timeout is only {timeout}s. "
+                f"Consolidation queries external services and can be slow; a low timeout "
+                f"frequently causes HTTP 408 (Request Timeout) errors. Consider increasing "
+                f"the 'timeout' setting to at least {self.CONSOLIDATE_CITATIONS_MIN_TIMEOUT}s "
+                f"(2-3 minutes is recommended)."
+            )
+
     def _handle_server_busy_retry(self, file_path, retry_func, *args, **kwargs):
         """Handle server busy (503) retry logic."""
         self.logger.warning(f"Server busy (503), retrying {file_path} after {self.config['sleep_time']} seconds")
@@ -209,7 +236,6 @@ class GrobidClient(ApiClient):
         size_str = str(size_str).upper().strip()
 
         # Extract number and unit
-        import re
         match = re.match(r'(\d+(?:\.\d+)?)\s*([KMGT]?B?)', size_str)
         if not match:
             return 10 * 1024 * 1024  # Default 10MB
@@ -329,7 +355,7 @@ class GrobidClient(ApiClient):
             input_path,
             output=None,
             n=10,
-            generateIDs=False,
+            generate_ids=False,
             consolidate_header=True,
             consolidate_citations=False,
             include_raw_citations=False,
@@ -345,6 +371,13 @@ class GrobidClient(ApiClient):
         start_time = time.time()
         batch_size_pdf = self.config["batch_size"]
 
+        # Warn if citation consolidation is requested with a short timeout: the
+        # consolidation step queries external services (e.g. CrossRef) and can
+        # be significantly slower, frequently resulting in HTTP 408 errors when
+        # the client-side timeout is too low.
+        # See https://github.com/grobidOrg/grobid-client-python/issues/54
+        self._warn_on_consolidation_timeout(consolidate_citations)
+
         # First pass: count all eligible files
         all_input_files = []
         for (dirpath, dirnames, filenames) in os.walk(input_path):
@@ -391,7 +424,7 @@ class GrobidClient(ApiClient):
                     input_path,
                     output,
                     n,
-                    generateIDs,
+                    generate_ids,
                     consolidate_header,
                     consolidate_citations,
                     include_raw_citations,
@@ -417,7 +450,7 @@ class GrobidClient(ApiClient):
                 input_path,
                 output,
                 n,
-                generateIDs,
+                generate_ids,
                 consolidate_header,
                 consolidate_citations,
                 include_raw_citations,
@@ -455,7 +488,7 @@ class GrobidClient(ApiClient):
             input_path,
             output,
             n,
-            generateIDs,
+            generate_ids,
             consolidate_header,
             consolidate_citations,
             include_raw_citations,
@@ -542,7 +575,7 @@ class GrobidClient(ApiClient):
                     selected_process,
                     service,
                     input_file,
-                    generateIDs,
+                    generate_ids,
                     consolidate_header,
                     consolidate_citations,
                     include_raw_citations,
@@ -639,7 +672,7 @@ class GrobidClient(ApiClient):
             self,
             service,
             pdf_file,
-            generateIDs,
+            generate_ids,
             consolidate_header,
             consolidate_citations,
             include_raw_citations,
@@ -667,7 +700,7 @@ class GrobidClient(ApiClient):
 
             # set the GROBID parameters
             the_data = {}
-            if generateIDs:
+            if generate_ids:
                 the_data["generateIDs"] = "1"
             if consolidate_header:
                 the_data["consolidateHeader"] = "1"
@@ -699,7 +732,7 @@ class GrobidClient(ApiClient):
                     self.process_pdf,
                     service,
                     pdf_file,
-                    generateIDs,
+                    generate_ids,
                     consolidate_header,
                     consolidate_citations,
                     include_raw_citations,
@@ -734,7 +767,7 @@ class GrobidClient(ApiClient):
             self,
             service,
             txt_file,
-            generateIDs,
+            generate_ids,
             consolidate_header,
             consolidate_citations,
             include_raw_citations,
@@ -777,7 +810,7 @@ class GrobidClient(ApiClient):
                     self.process_txt,
                     service,
                     txt_file,
-                    generateIDs,
+                    generate_ids,
                     consolidate_header,
                     consolidate_citations,
                     include_raw_citations,
@@ -840,7 +873,8 @@ def main():
         help="concurrency for service usage"
     )
     parser.add_argument(
-        "--generateIDs",
+        "--generate_ids", "--generateIDs",
+        dest="generate_ids",
         action="store_true",
         help="generate random xml:id to textual XML elements of the result files",
     )
@@ -870,12 +904,14 @@ def main():
         help="force re-processing pdf input files when tei output files already exist",
     )
     parser.add_argument(
-        "--teiCoordinates",
+        "--tei_coordinates", "--teiCoordinates",
+        dest="tei_coordinates",
         action="store_true",
         help="add the original PDF coordinates (bounding boxes) to the extracted elements",
     )
     parser.add_argument(
-        "--segmentSentences",
+        "--segment_sentences", "--segmentSentences",
+        dest="segment_sentences",
         action="store_true",
         help="segment sentences in the text content of the document with additional <s> elements",
     )
@@ -951,14 +987,14 @@ def main():
             exit(1)
 
     service = args.service
-    generateIDs = args.generateIDs
+    generate_ids = args.generate_ids
     consolidate_header = args.consolidate_header
     consolidate_citations = args.consolidate_citations
     include_raw_citations = args.include_raw_citations
     include_raw_affiliations = args.include_raw_affiliations
     force = args.force
-    tei_coordinates = args.teiCoordinates
-    segment_sentences = args.segmentSentences
+    tei_coordinates = args.tei_coordinates
+    segment_sentences = args.segment_sentences
     verbose = args.verbose
 
     if service is None or service not in valid_services:
@@ -973,7 +1009,7 @@ def main():
             input_path,
             output=output_path,
             n=n,
-            generateIDs=generateIDs,
+            generate_ids=generate_ids,
             consolidate_header=consolidate_header,
             consolidate_citations=consolidate_citations,
             include_raw_citations=include_raw_citations,

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/grobid_client_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: grobid-client-python
-Version: 0.1.3
+Version: 0.1.5
 Summary: Simple python client for GROBID REST services
 Author-email: Patrice Lopez <patrice.lopez@science-miner.com>
 Maintainer-email: Patrice Lopez <patrice.lopez@science-miner.com>, Luca Foppiano <lucanoro@duck.com>
@@ -353,13 +353,13 @@ grobid_client [OPTIONS] SERVICE
 
 | Option                       | Description                               |
 |------------------------------|-------------------------------------------|
-| `--generateIDs`              | Generate random XML IDs                   |
+| `--generate_ids`             | Generate random XML IDs                   |
 | `--consolidate_header`       | Consolidate header metadata               |
 | `--consolidate_citations`    | Consolidate bibliographic references      |
 | `--include_raw_citations`    | Include raw citation text                 |
 | `--include_raw_affiliations` | Include raw affiliation text              |
-| `--teiCoordinates`           | Add PDF coordinates to XML                |
-| `--segmentSentences`         | Segment sentences with coordinates        |
+| `--tei_coordinates`          | Add PDF coordinates to XML                |
+| `--segment_sentences`        | Segment sentences with coordinates        |
 | `--flavor`                   | Processing flavor for fulltext extraction |
 | `--json`                     | Convert TEI output to JSON format         |
 | `--markdown`                 | Convert TEI output to Markdown format     |
@@ -372,7 +372,7 @@ grobid_client [OPTIONS] SERVICE
 grobid_client --input ~/documents --output ~/results processFulltextDocument
 
 # High concurrency with coordinates
-grobid_client --input ~/pdfs --output ~/tei --n 20 --teiCoordinates processFulltextDocument
+grobid_client --input ~/pdfs --output ~/tei --n 20 --tei_coordinates processFulltextDocument
 
 # Process with JSON output
 grobid_client --input ~/pdfs --output ~/results --json processFulltextDocument
@@ -384,7 +384,7 @@ grobid_client --input ~/pdfs --output ~/results --markdown processFulltextDocume
 grobid_client --server https://grobid.example.com --input ~/citations.txt processCitationList
 
 # Force reprocessing with sentence segmentation and JSON output
-grobid_client --input ~/docs --force --segmentSentences --json processFulltextDocument
+grobid_client --input ~/docs --force --segment_sentences --json processFulltextDocument
 ```
 
 ### Python Library
@@ -421,10 +421,10 @@ client.process(
     input_path="/path/to/pdfs",
     output_path="/path/to/output",
     n=10,
-    generateIDs=True,
+    generate_ids=True,
     consolidate_header=True,
-    teiCoordinates=True,
-    segmentSentences=True
+    tei_coordinates=True,
+    segment_sentences=True
 )
 
 # Process with JSON output
@@ -517,6 +517,14 @@ settings.
 > Since version 0.0.12, the config file is optional. The client will use default localhost settings if no configuration
 > is provided.
 
+> [!WARNING]
+> **Citation consolidation and the `timeout` setting.** When `--consolidate_citations` (or `consolidate_citations=True`)
+> is enabled, GROBID queries external services (e.g. CrossRef) to enrich the extracted references. This is considerably
+> slower than a plain extraction, and a low `timeout` frequently causes `HTTP 408 (Request Timeout)` errors.
+> Set the `timeout` to at least **120 seconds (2-3 minutes recommended)** when consolidating citations. The client emits
+> a warning when consolidation is requested with a timeout below 120 seconds.
+> See [issue #54](https://github.com/grobidOrg/grobid-client-python/issues/54).
+
 ### Logging Configuration
 
 The client provides configurable logging with different verbosity levels. By default, only essential statistics and warnings are shown.
@@ -673,7 +681,7 @@ When using the `--json` flag, the client converts TEI XML output to a structured
 grobid_client --input pdfs/ --output results/ --json processFulltextDocument
 
 # JSON output with coordinates and sentence segmentation
-grobid_client --input pdfs/ --output results/ --json --teiCoordinates --segmentSentences processFulltextDocument
+grobid_client --input pdfs/ --output results/ --json --tei_coordinates --segment_sentences processFulltextDocument
 ```
 
 ```python
@@ -754,7 +762,7 @@ Competing interests statement...
 grobid_client --input pdfs/ --output results/ --markdown processFulltextDocument
 
 # Markdown output with coordinates and sentence segmentation
-grobid_client --input pdfs/ --output results/ --markdown --teiCoordinates --segmentSentences processFulltextDocument
+grobid_client --input pdfs/ --output results/ --markdown --tei_coordinates --segment_sentences processFulltextDocument
 ```
 
 ```python

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/grobid_client_python.egg-info/SOURCES.txt

@@ -7,6 +7,7 @@ example.py
 pyproject.toml
 pytest.ini
 requirements.txt
+.github/dependabot.yml
 .github/workflows/ci-build.yml
 .github/workflows/ci-release.yml
 grobid_client/__init__.py
@@ -24,6 +25,8 @@ grobid_client_python.egg-info/SOURCES.txt
 grobid_client_python.egg-info/dependency_links.txt
 grobid_client_python.egg-info/entry_points.txt
 grobid_client_python.egg-info/requires.txt
+grobid_client_python.egg-info/scm_file_list.json
+grobid_client_python.egg-info/scm_version.json
 grobid_client_python.egg-info/top_level.txt
 resources/20180928112135.png
 resources/20180928112138.csv

grobid_client_python-0.1.5/grobid_client_python.egg-info/scm_file_list.json

@@ -0,0 +1,63 @@
+{
+  "files": [
+    ".gitignore",
+    "example.py",
+    "pytest.ini",
+    "Readme.md",
+    "requirements.txt",
+    "pyproject.toml",
+    "MANIFEST.in",
+    "config.json",
+    "LICENSE",
+    ".github/dependabot.yml",
+    ".github/workflows/ci-build.yml",
+    ".github/workflows/ci-release.yml",
+    "resources/20180928112135.png",
+    "resources/20180928112138.csv",
+    "resources/test_txt/reference-strings-6.txt",
+    "resources/test_txt/reference-strings-1.txt",
+    "resources/test_txt/reference-strings-5.txt",
+    "resources/test_txt/reference-strings-7.txt",
+    "resources/test_txt/reference-strings-3.txt",
+    "resources/test_txt/reference-strings-2.txt",
+    "resources/test_txt/reference-strings-4.txt",
+    "resources/test_pdf/mjb3wlzxcb2mc-migowebupload-1766042162782.grobid.tei.xml",
+    "resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.pdf",
+    "resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml",
+    "grobid_client/client.py",
+    "grobid_client/grobid_client.py",
+    "grobid_client/__init__.py",
+    "grobid_client/format/validate_json_refs.py",
+    "grobid_client/format/TEI2LossyJSON_cli.py",
+    "grobid_client/format/TEI2LossyJSON.py",
+    "grobid_client/format/__main__.py",
+    "grobid_client/format/TEI2Markdown_cli.py",
+    "grobid_client/format/TEI2Markdown.py",
+    "grobid_client/format/__init__.py",
+    "tests/test_integration.py",
+    "tests/conftest.py",
+    "tests/run_tests.py",
+    "tests/test_config.json",
+    "tests/test_client.py",
+    "tests/test_conversions.py",
+    "tests/test_grobid_client.py",
+    "tests/__init__.py",
+    "tests/resources/article_withdrawn.grobid.tei.xml",
+    "tests/resources/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml",
+    "tests/resources/__init__.py",
+    "tests/resources/refs_offsets/10.1038_s41477-023-01501-1.json",
+    "tests/resources/refs_offsets/10.1371_journal.pone.0218311.json",
+    "tests/resources/refs_offsets/10.1038_s41477-023-01501-1.grobid.tei.xml",
+    "tests/resources/refs_offsets/10.1038_s41586-023-05895-y.grobid.tei.xml",
+    "tests/resources/refs_offsets/10.1038_s41598-023-32039-z.json",
+    "tests/resources/refs_offsets/10.7554_elife.78558.json",
+    "tests/resources/refs_offsets/10.1038_s41586-023-05895-y.json",
+    "tests/resources/refs_offsets/10.1038_s41598-023-32039-z.grobid.tei.xml",
+    "tests/resources/refs_offsets/2021.naacl-main.224.grobid.tei.xml",
+    "tests/resources/refs_offsets/10.1371_journal.pone.0218311.grobid.tei.xml",
+    "tests/resources/refs_offsets/10.7554_elife.78558.grobid.tei.xml",
+    "tests/resources/repeated_text/ijms-24-05988.grobid.tei.xml",
+    "tests/resources/repeated_text/ijms-24-05988.md",
+    "tests/resources/repeated_text/ijms-24-05988.json"
+  ]
+}

grobid_client_python-0.1.5/grobid_client_python.egg-info/scm_version.json

@@ -0,0 +1,8 @@
+{
+  "tag": "0.1.5",
+  "distance": 0,
+  "node": "g161e0f45189c8592b2e2c58e9638cc6218bc75fb",
+  "dirty": false,
+  "branch": "HEAD",
+  "node_date": "2026-07-23"
+}

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools", "setuptools-scm"]
 build-backend = "setuptools.build_meta"
 
 [tool.bumpversion]
-current_version = "0.1.3"
+current_version = "0.1.5"
 commit = "true"
 tag = "true"
 tag_name = "v{new_version}"

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/tests/test_grobid_client.py

@@ -284,7 +284,7 @@ class TestGrobidClient:
                 result = client.process_pdf(
                     'processFulltextDocument',
                     '/test/document.pdf',
-                    generateIDs=True,
+                    generate_ids=True,
                     consolidate_header=True,
                     consolidate_citations=False,
                     include_raw_citations=False,
@@ -308,7 +308,7 @@ class TestGrobidClient:
                 result = client.process_pdf(
                     'processFulltextDocument',
                     '/nonexistent/document.pdf',
-                    generateIDs=False,
+                    generate_ids=False,
                     consolidate_header=False,
                     consolidate_citations=False,
                     include_raw_citations=False,
@@ -335,7 +335,7 @@ class TestGrobidClient:
                 result = client.process_txt(
                     'processCitationList',
                     '/test/references.txt',
-                    generateIDs=False,
+                    generate_ids=False,
                     consolidate_header=False,
                     consolidate_citations=True,
                     include_raw_citations=True,
@@ -371,7 +371,7 @@ class TestGrobidClient:
                         result = client.process_pdf(
                             'processFulltextDocument',
                             '/test/document.pdf',
-                            generateIDs=False,
+                            generate_ids=False,
                             consolidate_header=False,
                             consolidate_citations=False,
                             include_raw_citations=False,
@@ -412,7 +412,7 @@ class TestGrobidClient:
                                 '/test',
                                 '/output',
                                 n=2,
-                                generateIDs=False,
+                                generate_ids=False,
                                 consolidate_header=False,
                                 consolidate_citations=False,
                                 include_raw_citations=False,
@@ -493,7 +493,7 @@ class TestEdgeCases:
             input_path='/test',
             output='/output',
             n=1,
-            generateIDs=False,
+            generate_ids=False,
             consolidate_header=False,
             consolidate_citations=False,
             include_raw_citations=False,
@@ -535,7 +535,7 @@ class TestEdgeCases:
             result = client.process_txt(
                 'processCitationList',
                 '/test/references.txt',
-                generateIDs=False,
+                generate_ids=False,
                 consolidate_header=False,
                 consolidate_citations=False,
                 include_raw_citations=False,
@@ -585,7 +585,7 @@ class TestEdgeCases:
                 result = client.process_pdf(
                     'processFulltextDocument',
                     '/test/document.pdf',
-                    generateIDs=False,
+                    generate_ids=False,
                     consolidate_header=False,
                     consolidate_citations=False,
                     include_raw_citations=False,
@@ -600,7 +600,7 @@ class TestEdgeCases:
                     result = client.process_pdf(
                         'processFulltextDocument',
                         '/test/document.pdf',
-                        generateIDs=False,
+                        generate_ids=False,
                         consolidate_header=False,
                         consolidate_citations=False,
                         include_raw_citations=False,

{grobid_client_python-0.1.3 → grobid_client_python-0.1.5}/tests/test_integration.py

@@ -171,7 +171,7 @@ class TestGrobidClientIntegration:
                                         '/test',
                                         '/output',
                                         n=2,
-                                        generateIDs=False,
+                                        generate_ids=False,
                                         consolidate_header=False,
                                         consolidate_citations=False,
                                         include_raw_citations=False,
@@ -332,7 +332,7 @@ class TestGrobidClientIntegration:
                                         '/test',
                                         '/output',
                                         n=5,  # 5 concurrent threads
-                                        generateIDs=False,
+                                        generate_ids=False,
                                         consolidate_header=False,
                                         consolidate_citations=False,
                                         include_raw_citations=False,