Merge branch 'main' into dependabot/pip/data_extractor/code/rule_base…

…d_pipeline/pillow-10.2.0

.pre-commit-config.yaml

@@ -65,7 +65,7 @@ repos:
 
   # Lint: Markdown
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.37.0
+    rev: v0.39.0
     hooks:
       - id: markdownlint
         args: ['--fix']
@@ -77,12 +77,12 @@ repos:
   #       args: ['--py37-plus']
 
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 23.11.0
+    rev: 24.1.1
     hooks:
       - id: black
 
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 23.11.0
+    rev: 24.1.1
     hooks:
       - id: black-jupyter
 
@@ -116,7 +116,7 @@ repos:
   #     ]
 
   - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
       - id: isort
 
@@ -150,7 +150,7 @@ repos:
   #   - id: codespell
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.7.1'
+    rev: 'v1.8.0'
     hooks:
       - id: mypy
 

data_extractor/code/rule_based_pipeline/rule_based_pipeline/AnalyzerTable.py

@@ -768,9 +768,11 @@ def find_kpi_with_indirect_years(self, kpispecs, bonus):
                             )
                         print_verbose(
                             7,
-                            ".........-> year found=" + str(kpi_year)
-                            if kpi_year != -1
-                            else "..........-> still nothing found. give up.",
+                            (
+                                ".........-> year found=" + str(kpi_year)
+                                if kpi_year != -1
+                                else "..........-> still nothing found. give up."
+                            ),
                         )
 
                     anywhere_match, anywhere_match_score = kpispecs.match_anywhere_on_page(self.htmlpage, it.this_id)

data_extractor/code/rule_based_pipeline/rule_based_pipeline/HTMLTable.py

@@ -1738,9 +1738,11 @@ def find_all_new_columns(tab1, tab2, tmp_rows, threshold_px):
                     if len(list_idx) > 1:
                         list_idx = sorted(
                             list_idx,
-                            key=lambda id_i: tab1.items[tab1.idx[id_i[1]]].pos_y
-                            if id_i[0] == 1
-                            else tab2.items[tab2.idx[id_i[1]]].pos_y,
+                            key=lambda id_i: (
+                                tab1.items[tab1.idx[id_i[1]]].pos_y
+                                if id_i[0] == 1
+                                else tab2.items[tab2.idx[id_i[1]]].pos_y
+                            ),
                         )
                         for k in range(len(list_idx) - 1):
                             id, ix = list_idx[k]

data_extractor/code/s3_communication.py

@@ -1,4 +1,5 @@
 """S3 communication tools."""
+
 import os
 import os.path as osp
 import pathlib

data_extractor/code/utils/s3_communication.py

@@ -1,4 +1,5 @@
 """S3 communication tools."""
+
 import os
 import os.path as osp
 import pathlib

data_extractor/docs/s3_communication.py

@@ -1,4 +1,5 @@
 """S3 communication tools."""
+
 import os
 import os.path as osp
 import pathlib

inception_transformer/inception_transformer.py

@@ -4,6 +4,7 @@
 #13 Project: INCEpTION to Pandas
 This function is used for the re-collection of marked answers out of an INCEpTION export.
 """
+
 import glob
 import json
 import logging

pyproject.toml

@@ -29,7 +29,7 @@ classifiers = [
 dependencies = [
   "Flask==2.3.2",
   "MarkupSafe==2.1.1",
-  "Pillow==10.1.0",
+  "Pillow==10.2.0",
   "Werkzeug",
   "boto3~=1.28.8",
   "cryptography==41.0.4",