chore(actions): Make Build Run.

Fix ruff and mypy errors.
Updated `env` to ensure existence of certain directories on startup.
Added missing deps.

Author: acederberg

.gitignore

@@ -45,3 +45,4 @@ blog/dev/_live_quarto_table_files/
 blog/projects/blog/typedoc
 blog/projects/blog/quartodoc
 blog/dsa/leetcode/calendar_2/_oops_files/
+.env.actions

acederbergio/env.py

@@ -7,6 +7,7 @@
 import logging
 import logging.config
 import logging.handlers
+import os
 import pathlib
 import secrets
 from os import environ
@@ -82,7 +83,11 @@ def require(varname: str, default: str | None = None) -> str:
 
 
 def require_path(
-    varname: str, default: pathlib.Path | None = None, *, strict: bool = True
+    varname: str,
+    default: pathlib.Path | None = None,
+    *,
+    strict: bool = True,
+    ensure_dir: bool = False,
 ) -> pathlib.Path:
     """Require a setting  from environment that is an existing path.
 
@@ -96,12 +101,16 @@ def require_path(
 
     var = get(varname)
     if var is not None:
-        return pathlib.Path(var).resolve(strict=strict)
-
-    if default is None:
+        output = pathlib.Path(var)
+    elif default is None:
         raise ValueError(f"Value `{var}` for `{varname}` is falsy.")
+    else:
+        output = default
 
-    return default.resolve(strict=strict)
+    if ensure_dir and not os.path.exists(output := output.resolve()):
+        os.mkdir(output)
+
+    return output.resolve(strict=strict)
 
 
 def create_validator(varname: str, default: str | None = None):
@@ -160,24 +169,19 @@ def validator(v: Any) -> Any:
     WORKDIR = ROOT
     PYPROJECT_TOML = ROOT / "pyproject.toml"
     CONFIGS = require_path("config_dir", ROOT / "config", strict=False)
-
-    BUILD = BLOG / "build"
-    ICONS = BLOG / "icons"
-
 else:
     # NOTE:
     WORKDIR = require_path("workdir")
     BLOG = require_path("blog", WORKDIR / "blog")
     PYPROJECT_TOML = require_path("pyproject_toml", WORKDIR / "pyproject.toml")
     CONFIGS = require_path("config_dir", pathlib.Path.home() / "config", strict=False)
 
-    BUILD = require_path("build", BLOG / "build")
-    ICONS = require_path("icons", BLOG / "icons")
-
+BUILD = require_path("build", BLOG / "build", ensure_dir=True)
+ICONS = require_path("icons", BLOG / "icons", ensure_dir=True)
 VERBOSE = require("verbose", "0") != "0"
 TEMPLATES = require_path("templates", SCRIPTS / "templates")
-ICONS_SETS = require_path("icon_sets", ICONS / "sets")
-BUILD_JSON = require_path("build_json", BLOG / "build.json")
+ICONS_SETS = require_path("icon_sets", ICONS / "sets", ensure_dir=True)
+BUILD_JSON = require_path("build_json", BLOG / "build.json", strict=False)
 
 LEVEL = require("log_level", "INFO").upper()
 LEVEL_FILTERS = require("log_level_filters", LEVEL).upper()
@@ -239,13 +243,16 @@ def create_logging_config() -> dict[str, Any]:
         config_pandoc_filters = {"level": "INFO", "handlers": ["_socket"]}
     else:
         # NOTE: Add build logs to build in ci mode.
+        log_file = BUILD / "build.jsonl"
+        log_file.touch()
+
         handlers.update(
             {
                 "_file": {
                     "class": "logging.FileHandler",
                     "level": LEVEL_FILTERS,
                     "formatter": "json",
-                    "filename": str(BUILD / "build.jsonl"),
+                    "filename": str(log_file),
                 }
             }
         )

acederbergio/pdf.py

@@ -1,21 +1,6 @@
-import yaml
-
-yaml.safe_load(
-    """
-    some: yaml
-    it: should
-    be: highlighted
-    """
-)
-
-# | Yes! Thank god.
-# |
-# | some: yaml
-# | it: should
-# | be: highlighted
-
 import asyncio
 import enum
+import hashlib
 import math
 import pathlib
 from typing import Annotated, Any, ClassVar, Generator, Optional, Protocol, Self
@@ -28,7 +13,6 @@
 import pypdf as pdf
 import rake_nltk as rake
 import typer
-from gitdb.util import hashlib
 
 from acederbergio import db, env, util
 
@@ -172,7 +156,7 @@ def createDF(cls, text: str, **rake_kwargs) -> pd.DataFrame:
 
         df = df.transpose()  # .rename(columns=[metric.name for metric in rake.])
         df.reset_index(inplace=True)
-        df.columns = MetricsColumns
+        df.columns = MetricsColumns  # type: ignore[assignment]
 
         return df
 
@@ -183,7 +167,7 @@ def create(
         """Transform a compatible dataframe into this object."""
 
         metrics = {row[0]: MetricsRow.fromDFRow(row) for _, row in df.iterrows()}
-        return cls(metrics=metrics, text=text, metadata=metadata)  # type: ignore[missing-args]
+        return cls(metrics=metrics, text=text, metadata=metadata)  # type: ignore[call-arg,arg-type]
 
     @classmethod
     def match_text(cls, text: str) -> dict:
@@ -253,7 +237,7 @@ def to_df(self) -> pd.DataFrame:
 
     def trie(self) -> dict[str, Any]:
 
-        root = {}
+        root: dict[str, Any] = {}
 
         for phrase, metrics in self.metrics.items():
             node = root
@@ -274,7 +258,7 @@ def chunks(self) -> Generator[dict[str, Any], None, None]:
         tokenized = nltk.tokenize.word_tokenize(self.text)
         k, n = 0, len(tokenized)
 
-        phrase = []
+        phrase: list[str] = []
         while k < n:
             word = tokenized[k]
             word_lower = word.lower()
@@ -585,7 +569,9 @@ def cli_highlight(
         util.CONSOLE.print(res.highlight_html())
         return
 
-    def highlighter(phrase: str, match: str, *, metrics: Metrics | None = None) -> str:
+    def highlighter(
+        phrase: str, match: str, *, metrics: MetricsRow | None = None
+    ) -> str:
         print("metrics", metrics)
         # if match is None:
         #     return phrase

acederbergio/util.py

@@ -3,7 +3,7 @@
 import logging.handlers
 import queue
 from datetime import datetime
-from typing import Annotated, Any, Mapping, overload
+from typing import Annotated, Any, Mapping
 
 import pandas
 import pydantic
@@ -99,8 +99,7 @@ def print_yaml(
         code = MagicEncoder(kwargs_model_dump, indent=2).encode(data)
 
     if not pretty:
-        print(code)
-        return
+        return None
 
     s = rich.syntax.Syntax(
         code,