Merge pull request #672 from ostefano/pandas2

Update pandas and pandas_ods_reader and patch ods_enrich
MISP · Jul 19, 2024 · 4711dcb · 4711dcb
2 parents 5b15b4a + a52da45
commit 4711dcb
Show file tree

Hide file tree

Showing 3 changed files with 72 additions and 57 deletions.
diff --git a/Pipfile b/Pipfile
@@ -54,8 +54,8 @@ ODTReader = { git = "https://github.com/cartertemm/ODTReader.git/" }
 python-pptx = "*"
 python-docx = "*"
 ezodf = "*"
-pandas = "==1.3.5"
-pandas_ods_reader = "==0.1.2"
+pandas = "*"
+pandas_ods_reader = "*"
 pdftotext = "*"
 lxml = "*"
 xlrd = "*"
@@ -77,7 +77,7 @@ crowdstrike-falconpy = "0.9.0"
 censys = "2.0.9"
 mwdblib = "3.4.1"
 ndjson = "0.3.1"
-Jinja2 = "3.1.2"
+Jinja2 = ">=3.1.2"
 mattermostdriver = "7.3.2"
 openpyxl = "*"
 slack-sdk = "3.27.1"

diff --git a/Pipfile.lock b/Pipfile.lock
diff --git a/misp_modules/modules/expansion/ods_enrich.py b/misp_modules/modules/expansion/ods_enrich.py
@@ -36,7 +36,9 @@ def handler(q=False):
     num_sheets = len(doc.sheets)
     try:
         for i in range(0, num_sheets):
-            ods = pandas_ods_reader.algo.read_data(pandas_ods_reader.parsers.ods, ods_file, i, headers=False)
+            rows = pandas_ods_reader.parsers.ods.get_rows(doc, i)
+            ods = pandas_ods_reader.algo.parse_data(pandas_ods_reader.parsers.ods, rows, headers=False, columns=[], skiprows=0)
+            ods = pandas_ods_reader.utils.sanitize_df(ods)
             ods_content = ods_content + "\n" + ods.to_string(max_rows=None)
         return {'results': [{'types': ['freetext'], 'values': ods_content, 'comment': ".ods-to-text from file " + filename},
                             {'types': ['text'], 'values': ods_content, 'comment': ".ods-to-text from file " + filename}]}