Better errors when loading CSV files

.gitignore

@@ -0,0 +1,219 @@
+# PyCharm
+.idea/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

pyproject.toml

@@ -45,8 +45,8 @@ norecursedirs = [
     "tests/helpers",
 ]
 
-[tool.uv]
-dev-dependencies = [
-    "coverage[toml]>=7.6.1",
-    "pytest ~= 8.3",
+[dependency-groups]
+dev = [
+  "coverage[toml]>=7.6.1",
+  "pytest~=8.3",
 ]

src/fediblockhole/blocklists.py

@@ -1,16 +1,18 @@
-"""Parse various blocklist data formats
-"""
+"""Parse various blocklist data formats"""
 
 from __future__ import annotations
 
 import csv
 import json
 import logging
 from dataclasses import dataclass, field
-from typing import Iterable
+from typing import Iterable, TYPE_CHECKING
 
 from .const import BlockAudit, BlockSeverity, DomainBlock
 
+if TYPE_CHECKING:
+    from typing import Any
+
 log = logging.getLogger("fediblockhole")
 
 
@@ -21,7 +23,7 @@ class Blocklist:
     A Blocklist is a list of DomainBlocks from an origin
     """
 
-    origin: str = None
+    origin: str | None = None
     blocks: dict[str, DomainBlock] = field(default_factory=dict)
 
     def __len__(self):
@@ -50,7 +52,7 @@ class BlockAuditList:
     A BlockAuditlist is a list of BlockAudits from an origin
     """
 
-    origin: str = None
+    origin: str | None = None
     blocks: dict[str, BlockAudit] = field(default_factory=dict)
 
     def __len__(self):
@@ -81,43 +83,61 @@ class BlocklistParser(object):
 
     def __init__(
         self,
-        import_fields: list = ["domain", "severity"],
+        import_fields: list[str] | None = None,
         max_severity: str = "suspend",
     ):
         """Create a Parser
 
         @param import_fields: an optional list of fields to limit the parser to.
             Ignore any fields in a block item that aren't in import_fields.
         """
+        if import_fields is None:
+            import_fields = ["domain", "severity"]
         self.import_fields = import_fields
         self.max_severity = BlockSeverity(max_severity)
+        self._current_origin = None
 
-    def preparse(self, blockdata) -> Iterable:
+    def preparse(self, blockdata: Any) -> Iterable:
         """Some raw datatypes need to be converted into an iterable"""
         raise NotImplementedError
 
-    def parse_blocklist(self, blockdata, origin: str = None) -> Blocklist:
+    def parse_blocklist(self, blockdata: Any, origin: str | None = None) -> Blocklist:
         """Parse an iterable of blocklist items
         @param blocklist: An Iterable of blocklist items
         @returns: A dict of DomainBlocks, keyed by domain
         """
+        self._current_origin = origin
         if self.do_preparse:
             blockdata = self.preparse(blockdata)
 
         parsed_list = Blocklist(origin)
         for blockitem in blockdata:
-            block = self.parse_item(blockitem)
+            try:
+                block = self.parse_item(blockitem)
+            except ValueError as e:
+                msg = f"Error while loading {self._get_location(blockdata, blockitem)} from {self._current_origin}: {e}"
+                raise ValueError(msg) from e
             parsed_list.blocks[block.domain] = block
+        # Reset origin
+        self._current_origin = None
         return parsed_list
 
-    def parse_item(self, blockitem) -> DomainBlock:
+    def parse_item(self, blockitem: Any) -> DomainBlock:
         """Parse an individual block item
 
         @param blockitem: an individual block to be parsed
         @param import_fields: fields of a block we will import
         """
         raise NotImplementedError
 
+    def _get_location(self, blockdata: Iterable, blockitem: Any) -> str | None:
+        """Parsers can implement a custom function to return the current parsing location
+
+        @param blockdata: The iterable of data. Might be used by the function to glean the location from
+        @param blockitem: The current data item. Might be used by the function to glean the location from
+        """
+        return None
+
 
 class BlocklistParserJSON(BlocklistParser):
     """Parse a JSON formatted blocklist"""
@@ -176,10 +196,22 @@ class BlocklistParserCSV(BlocklistParser):
     """
 
     do_preparse = True
+    required_fieldnames = ["domain"]
+
+    def _get_location(self, blockdata: Iterable, blockitem: Any) -> str | None:
+        assert isinstance(blockdata, csv.DictReader)
+        assert isinstance(blockitem, dict)
+        return f"Line {blockdata.line_num}: {blockitem}"
 
     def preparse(self, blockdata) -> Iterable:
         """Use a csv.DictReader to create an iterable from the blockdata"""
-        return csv.DictReader(blockdata.split("\n"))
+        reader = csv.DictReader(blockdata.split("\n"))
+        assert reader.fieldnames is not None
+        for fieldname in self.required_fieldnames:
+            if fieldname not in reader.fieldnames:
+                msg = f"CSV from '{self._current_origin}' is missing the '{fieldname}' field. Maybe the header row is missing?"
+                raise KeyError(msg)
+        return reader
 
     def parse_item(self, blockitem: dict) -> DomainBlock:
         # Coerce booleans from string to Python bool
@@ -211,6 +243,7 @@ class BlocklistParserMastodonCSV(BlocklistParserCSV):
     """
 
     do_preparse = True
+    required_fieldnames = ["#domain"]
 
     def parse_item(self, blockitem: dict) -> DomainBlock:
         """Build a new blockitem dict with new un-#ed keys"""
@@ -228,6 +261,8 @@ class RapidBlockParserCSV(BlocklistParserCSV):
     RapidBlock CSV blocklists are just a newline separated list of domains.
     """
 
+    required_fieldnames = []
+
     def preparse(self, blockdata) -> Iterable:
         """Prepend a 'domain' field header to the data"""
         log.debug(f"blockdata: {blockdata[:100]}")