Merge pull request dod-cyber-crime-center#48 from kchason/python-3.13

Python 3.13 Support

Author: dc3-tsd

.github/workflows/ci.yml

@@ -7,7 +7,7 @@ on:
 env:
   # The Python version for the build jobs as well as the primary one for the test and artifact generation. This MUST be
   # in the python-version matrix in the `test` job.
-  PYTHON_VERSION: "3.12"  
+  PYTHON_VERSION: "3.13"  
 jobs:
   test:      
     runs-on: ubuntu-latest
@@ -16,7 +16,7 @@ jobs:
         # This allows the pipeline to be run against multiple Python versions. eg. [3.6, 3.7, 3.8, 3.9, 3.10]. This results
         # in linting and unit tests running for all listed versions as well as the creation of packages and wheels on
         # creation of a tag in Git.
-        python-version: [ "3.8", "3.10", "3.12" ]
+        python-version: [ "3.8", "3.10", "3.12", "3.13" ]
 
     steps:
       # Get the code from the repository to be packaged

.gitlab-ci.yml

@@ -10,7 +10,7 @@ default:
   tags:
     - docker
     - devnet
-  image: python:3.11
+  image: python:3.13
 
 stages:
   - Lint
@@ -30,9 +30,9 @@ FlakeLint:
     - pip install .
     - pip install -q flake8
     # stop the build if there are Python syntax errors or undefined names
-    - flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+    - flake8 ./sqlite_dissect/ --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
+    - flake8 ./sqlite_dissect/ --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
 PyTest:
   stage: Test

sqlite_dissect/file/schema/column.py

@@ -27,7 +27,7 @@ def __init__(self, index, column_text, comments=None):
         logger = getLogger(LOGGER_NAME)
 
         self.index = index
-        self.column_text = sub("\s\s+", " ", column_text.strip())
+        self.column_text = sub(r"\s\s+", " ", column_text.strip())
 
         """
 
@@ -112,7 +112,7 @@ def __init__(self, index, column_text, comments=None):
             raise MasterSchemaRowParsingError(log_message)
 
         # Update the parsed column text replacing any whitespace with a single " " character and stripping it
-        parsed_column_text = sub("\s\s+", " ", parsed_column_text.strip())
+        parsed_column_text = sub(r"\s\s+", " ", parsed_column_text.strip())
 
         # Check the comments sent in for validity
         if comments:
@@ -188,7 +188,7 @@ def __init__(self, index, column_text, comments=None):
             # Get the next segment
             segment = remaining_column_text[:segment_index + 1]
 
-            if (len(segment) == len(remaining_column_text) or match("\w", remaining_column_text[segment_index + 1])) \
+            if (len(segment) == len(remaining_column_text) or match(r"\w", remaining_column_text[segment_index + 1])) \
                 and ColumnDefinition._is_column_constraint_preface(segment):
 
                 """
@@ -222,8 +222,8 @@ def __init__(self, index, column_text, comments=None):
 
                 """
 
-                segment = sub("\s*\(\s*", "(", segment)
-                segment = sub("\s*\)\s*", ")", segment)
+                segment = sub(r"\s*\(\s*", "(", segment)
+                segment = sub(r"\s*\)\s*", ")", segment)
                 segment = segment.strip()
 
                 # Convert it to all uppercase for the derived data type name
@@ -325,7 +325,7 @@ def _get_column_name_and_remaining_sql(index, column_text):
         elif column_text[0] == "[":
 
             # The column name is surrounded by brackets
-            match_object = match("^\[(.*?)\]", column_text)
+            match_object = match(r"^\[(.*?)\]", column_text)
 
             if not match_object:
                 log_message = "No bracket match found for sql column definition: {} with text: {}."
@@ -427,15 +427,15 @@ def _get_data_type(derived_data_type):
         derived_data_type = derived_data_type.upper()
 
         # Remove any parenthesis along with numerical values
-        derived_data_type = sub("\(.*\)$", "", derived_data_type)
+        derived_data_type = sub(r"\(.*\)$", "", derived_data_type)
 
         # Replace spaces with underscores
         derived_data_type = derived_data_type.replace(" ", "_")
 
         for data_type in DATA_TYPE:
 
             # We remove any numerical values from the end since sqlite does not recognize them in the data types
-            if sub("_\d+.*$", "", data_type) == derived_data_type:
+            if sub(r"_\d+.*$", "", data_type) == derived_data_type:
                 return data_type
 
         # If no data type was found we return an invalid data type
@@ -544,15 +544,15 @@ def _is_column_constraint_preface(segment):
             Note: When the check is done on the segment, we check the next character is not one of the allowed
                   characters in a column name, data type, etc. to make sure the constraint preface is not the 
                   beginning of a longer name where it is not actually a constraint preface (example: primaryEmail).
-                  The "\w" regular expression when no LOCALE and UNICODE flags are set will be equivalent to the set:
+                  The regular expression when no LOCALE and UNICODE flags are set will be equivalent to the set:
                   [a-zA-Z0-9_].
 
             """
 
             # Check to see if the segment starts with the column constraint preface
             if segment.upper().startswith(column_constraint_preface):
                 if not (len(column_constraint_preface) + 1 <= len(segment)
-                        and match("\w", segment[len(column_constraint_preface)])):
+                        and match(r"\w", segment[len(column_constraint_preface)])):
                     return True
 
         return False

sqlite_dissect/file/schema/master.py

@@ -1414,7 +1414,7 @@ class for parsing.  This was decided to be the best way to associate comments ba
                         Note: When the check is done on the definition, we check the next character is not one of the
                               allowed characters in a column name to make sure the constraint preface is not the
                               beginning of a longer column name where it is not actually a constraint preface
-                              (example: primaryEmail).  The r'\w' regular expression when no LOCALE and UNICODE flags
+                              (example: primaryEmail).  The regular expression when no LOCALE and UNICODE flags
                               are set will be equivalent to the set: [a-zA-Z0-9_].
 
                         """