Merge pull request #132 from MartinBernstorff/mb/rewrite_entrypoint

refactor: rewrite entrypoint

.github/dependabot.yml

@@ -14,3 +14,5 @@ updates:
     commit-message:
       prefix: "deps:"
       include: "scope"
+    ignore:
+      - dependency-name: invoke

.vscode/settings.json

@@ -3,5 +3,6 @@
         "tests"
     ],
     "python.testing.unittestEnabled": false,
-    "python.testing.pytestEnabled": true
+    "python.testing.pytestEnabled": true,
+    "python.analysis.typeCheckingMode": "strict"
 }

application/main.py

@@ -20,23 +20,22 @@
 """
 
 import json
-import os
 import urllib.request
 from collections import defaultdict
 from pathlib import Path
 from typing import Any, Dict
 
 from docopt import docopt
+from personal_mnemonic_medium.card_pipeline import CardPipeline
 from personal_mnemonic_medium.exporters.anki.globals import (
     CONFIG,
     VERSION,
-    VERSION_LOG,
 )
 from personal_mnemonic_medium.exporters.anki.package_generator import (
     AnkiPackageGenerator,
 )
 from personal_mnemonic_medium.exporters.anki.sync import sync_deck
-from personal_mnemonic_medium.markdown_to_ankicard import markdown_to_ankicard
+from personal_mnemonic_medium.note_factories.markdown import MarkdownNoteFactory
 from personal_mnemonic_medium.prompt_extractors.cloze_extractor import (
     ClozePromptExtractor,
 )
@@ -103,13 +102,17 @@ def apply_arguments(arguments: Any) -> None:
 def main():
     """Run the thing."""
     apply_arguments(docopt(__doc__, version=VERSION))
-    initial_dir = Path(__file__).parent
     recur_dir = Path(CONFIG["recur_dir"])
-    version_log = Path(CONFIG["version_log"])
 
-    cards = markdown_to_ankicard(
-        dir_path=recur_dir,
-        extractors=[QAPromptExtractor(), ClozePromptExtractor()],
+    cards = CardPipeline(
+        document_factory=MarkdownNoteFactory(),  # Step 1, get the documents
+        prompt_extractors=[  # Step 2, get the prompts from the documents
+            QAPromptExtractor(),
+            ClozePromptExtractor(),
+        ],
+        card_exporter=AnkiPackageGenerator(),  # Step 3, get the cards from the prompts
+    ).run(
+        input_path=recur_dir,
     )
 
     decks = defaultdict(list)
@@ -121,13 +124,10 @@ def main():
         deck_bundle = AnkiPackageGenerator().cards_to_deck_bundle(cards=decks[deck])
         sync_deck(
             deck_bundle=deck_bundle,
-            dir_path=initial_dir,
+            dir_path=Path(__file__).parent,
             max_wait_for_ankiconnect=30,
         )
 
-    os.chdir(initial_dir)
-    json.dump(VERSION_LOG, Path(version_log).open("w"))
-
 
 if __name__ == "__main__":
     main()

pyproject.toml

@@ -34,7 +34,7 @@ dev = [
   "ruff>=0.0.254",
   "black[jupyter]>=22.8.0",
   "pandas-stubs>=0.0.0",    # type stubs for pandas
-  "invoke==2.2.0",
+  "invoke==2.1.0",
 ]
 tests = [
   "pytest>=7.1.3",
@@ -67,6 +67,8 @@ documentation = "https://MartinBernstorff.github.io/personal-mnemonic-medium/"
 [tool.pyright]
 exclude = [".*venv*", ".tox", "*.apkg"]
 pythonPlatform = "Darwin"
+typeCheckingMode = "basic"
+
 
 [tool.ruff]
 # Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.

src/personal_mnemonic_medium/card_pipeline.py

@@ -0,0 +1,47 @@
+from collections.abc import Sequence
+from pathlib import Path
+from typing import List
+
+from personal_mnemonic_medium.exporters.anki.card_types.base import AnkiCard
+from personal_mnemonic_medium.exporters.base import CardExporter
+from personal_mnemonic_medium.note_factories.base import DocumentFactory
+from personal_mnemonic_medium.note_factories.note import Document
+from personal_mnemonic_medium.prompt_extractors.base import PromptExtractor
+from personal_mnemonic_medium.prompt_extractors.prompt import Prompt
+
+
+class CardPipeline:
+    def __init__(
+        self,
+        document_factory: DocumentFactory,
+        prompt_extractors: Sequence[PromptExtractor],
+        card_exporter: CardExporter,
+    ) -> None:
+        self.document_factory = document_factory
+        self.prompt_extractors = prompt_extractors
+        self.card_exporter = card_exporter
+
+    def run(
+        self,
+        input_path: Path,
+    ) -> List[AnkiCard]:
+        notes: List[Document] = []
+        if input_path.is_dir():
+            notes += list(self.document_factory.get_notes_from_dir(dir_path=input_path))
+
+        if not input_path.is_dir():
+            note_from_file = self.document_factory.get_note_from_file(
+                file_path=input_path,
+            )
+            notes.append(note_from_file)
+
+        collected_prompts: list[Prompt] = []
+
+        for extractor in self.prompt_extractors:
+            for note in notes:
+                collected_prompts += extractor.extract_prompts(note)
+
+        cards: list[AnkiCard] = self.card_exporter.prompts_to_cards(
+            prompts=collected_prompts,
+        )
+        return cards

src/personal_mnemonic_medium/exporters/anki/package_generator.py

@@ -8,14 +8,16 @@
 from dataclasses import dataclass
 from pathlib import Path
 from shutil import copyfile
-from typing import Any, List, Set, Union
+from typing import Any, List, Set
 
 import genanki
 
 from personal_mnemonic_medium.exporters.anki.card_types.base import AnkiCard
 from personal_mnemonic_medium.exporters.anki.card_types.cloze import AnkiCloze
 from personal_mnemonic_medium.exporters.anki.card_types.qa import AnkiQA
+from personal_mnemonic_medium.exporters.base import CardExporter
 from personal_mnemonic_medium.prompt_extractors.cloze_extractor import ClozePrompt
+from personal_mnemonic_medium.prompt_extractors.prompt import Prompt
 from personal_mnemonic_medium.prompt_extractors.qa_extractor import QAPrompt
 from personal_mnemonic_medium.utils.hasher import simple_hash
 
@@ -52,7 +54,7 @@ def save_deck_to_file(self, output_path: Path) -> Path:
         return output_path
 
 
-class AnkiPackageGenerator:
+class AnkiPackageGenerator(CardExporter):
     """Generates an anki package from a list of anki cards"""
 
     def __init__(self) -> None:
@@ -100,11 +102,11 @@ def cards_to_deck(
 
     def prompts_to_cards(
         self,
-        prompts: Sequence[Union[QAPrompt, ClozePrompt]],
+        prompts: Sequence[Prompt],
     ) -> List[AnkiCard]:
         """Takes an iterable of prompts and turns them into AnkiCards"""
 
-        cards = []
+        cards: list[AnkiCard] = []
 
         for prompt in prompts:
             if isinstance(prompt, QAPrompt):
@@ -120,7 +122,9 @@ def prompts_to_cards(
                     fields=[prompt.content],
                     source_prompt=prompt,
                 )
+            else:
+                raise NotImplementedError(f"Prompt type {type(prompt)} not supported.")
 
-            cards += [card]  # type: ignore
+            cards += [card]
 
         return cards

src/personal_mnemonic_medium/exporters/base.py

@@ -0,0 +1,11 @@
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+
+from personal_mnemonic_medium.exporters.anki.card_types.base import AnkiCard
+from personal_mnemonic_medium.prompt_extractors.prompt import Prompt
+
+
+class CardExporter(ABC):
+    @abstractmethod
+    def prompts_to_cards(self, prompts: Sequence[Prompt]) -> list[AnkiCard]:
+        pass

src/personal_mnemonic_medium/note_factories/base.py

@@ -0,0 +1,15 @@
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+from pathlib import Path
+
+from personal_mnemonic_medium.note_factories.note import Document
+
+
+class DocumentFactory(ABC):
+    @abstractmethod
+    def get_notes_from_dir(self, dir_path: Path) -> Sequence[Document]:
+        pass
+
+    @abstractmethod
+    def get_note_from_file(self, file_path: Path) -> Document:
+        pass

src/personal_mnemonic_medium/note_factories/markdown.py

@@ -1,14 +1,16 @@
 import os
 import re
+from collections.abc import Sequence
 from pathlib import Path
-from typing import List, Optional
+from typing import Optional
 
 from tqdm import tqdm
 
+from personal_mnemonic_medium.note_factories.base import DocumentFactory
 from personal_mnemonic_medium.note_factories.note import Document
 
 
-class MarkdownNoteFactory:
+class MarkdownNoteFactory(DocumentFactory):
     def __init__(self, cut_note_after: str = "# Backlinks"):
         """Create a new MarkdownNoteFactory.
 
@@ -50,7 +52,7 @@ def get_note_from_file(self, file_path: Path) -> Optional[Document]:
                 source_path=file_path,
             )
 
-    def get_notes_from_dir(self, dir_path: Path) -> List[Document]:
+    def get_notes_from_dir(self, dir_path: Path) -> Sequence[Document]:
         notes: list[Document] = []
 
         for parent_dir, _, files in os.walk(dir_path):

src/personal_mnemonic_medium/prompt_extractors/base.py

@@ -0,0 +1,11 @@
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+
+from personal_mnemonic_medium.note_factories.note import Document
+from personal_mnemonic_medium.prompt_extractors.prompt import Prompt
+
+
+class PromptExtractor(ABC):
+    @abstractmethod
+    def extract_prompts(self, note: Document) -> Sequence[Prompt]:
+        pass

src/personal_mnemonic_medium/prompt_extractors/cloze_extractor.py

@@ -1,8 +1,10 @@
 import hashlib
 import re
+from collections.abc import Sequence
 from typing import Any, List, Optional
 
 from personal_mnemonic_medium.note_factories.note import Document
+from personal_mnemonic_medium.prompt_extractors.base import PromptExtractor
 from personal_mnemonic_medium.prompt_extractors.prompt import Prompt
 
 
@@ -12,17 +14,17 @@ def __init__(self, content: str, *args: Any, **kwargs: Any):
         self.content = content
 
 
-class ClozePromptExtractor:
+class ClozePromptExtractor(PromptExtractor):
     def __init__(self) -> None:
         pass
 
     @staticmethod
-    def break_string_by_two_or_more_newlines(string: str) -> List[str]:
+    def _break_string_by_two_or_more_newlines(string: str) -> List[str]:
         """Break string into a list by 2+ newlines in a row."""
         return re.split(r"(\n\n)+", string)
 
     @staticmethod
-    def has_cloze(string: str) -> bool:
+    def _has_cloze(string: str) -> bool:
         if (
             len(re.findall(r"{.*}", string)) > 0
             and "BearID" not in string  # Exclude BearID
@@ -35,7 +37,7 @@ def has_cloze(string: str) -> bool:
         return False
 
     @staticmethod
-    def replace_cloze_id_with_unique(
+    def _replace_cloze_id_with_unique(
         string: str,
         selected_cloze: Optional[str] = None,
     ) -> str:
@@ -63,17 +65,17 @@ def replace_cloze_id_with_unique(
 
         return string
 
-    def extract_prompts(self, note: Document) -> List[ClozePrompt]:
+    def extract_prompts(self, note: Document) -> Sequence[ClozePrompt]:
         prompts = []
 
-        blocks = self.break_string_by_two_or_more_newlines(note.content)
+        blocks = self._break_string_by_two_or_more_newlines(note.content)
 
         for block_string in blocks:
-            if self.has_cloze(block_string):
+            if self._has_cloze(block_string):
                 clozes = re.findall(r"{(?!BearID).[^}]*}", block_string)
 
                 for selected_cloze in clozes:
-                    prompt_content = self.replace_cloze_id_with_unique(
+                    prompt_content = self._replace_cloze_id_with_unique(
                         block_string,
                         selected_cloze=selected_cloze,
                     )