tha-csv-runner 0.2.0__tar.gz → 0.2.2__tar.gz

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tha-csv-runner
-Version: 0.2.0
+Version: 0.2.2
 Summary: Run a function over every row of a CSV — with progress, header validation, and structured per-row errors.
 Project-URL: Homepage, https://github.com/tha-guy-nate/tha-csv-runner
 Project-URL: Issues, https://github.com/tha-guy-nate/tha-csv-runner/issues
@@ -47,7 +47,7 @@ def process(row: dict) -> None:
 
 runner = ThaCSV()
 
-runner.read("Step 1 of 1", "data.csv", ["name", "email"], process)
+rows = runner.read("Step 1 of 1", "data.csv", ["name", "email"], process)
 runner.write("Step 1 of 1", "output.csv")
 ```
 
@@ -55,7 +55,7 @@ runner.write("Step 1 of 1", "output.csv")
 
 1. Opens the CSV and validates that all `required_headers` are present — raises immediately if any are missing
 2. Iterates every row with a `tqdm` progress bar labelled with `desc`
-3. Calls your `processor(row)` function — if it raises, that row is marked as an error and processing continues
+3. Calls your `validator(row)` function — if it raises, that row is marked as an error and processing continues
 4. Appends three columns to every row: `row number`, `row status`, and `message`
    - On success: `row status` and `message` are blank
    - On error: `row status = "error"`, `message = str(exception)`
@@ -76,15 +76,14 @@ runner.read(
     "Step 2 of 10",          # progress bar label — pass None to use the filename
     "data.csv",              # path to input CSV
     ["a", "b"],              # columns that must exist — raises ConfigError if missing
-    processor=my_func,       # optional: callable(row: dict) -> None
-    sample=100,              # optional: process only the first N rows
+    validator=my_func,       # optional: callable(row: dict) -> None
     enrich=True,             # optional: set False to skip row number/status/message columns
 )
 ```
 
-Reads and processes all rows. Results are stored in `runner.rows` as a list of dicts.
+Reads and processes all rows. Returns the rows as a `list[dict]` (same object as `runner.rows`).
 
-When `enrich=False`, processor exceptions are re-raised instead of captured.
+When `enrich=False`, validator exceptions are re-raised instead of captured.
 
 ### `runner.write()`
 

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/README.md

@@ -22,7 +22,7 @@ def process(row: dict) -> None:
 
 runner = ThaCSV()
 
-runner.read("Step 1 of 1", "data.csv", ["name", "email"], process)
+rows = runner.read("Step 1 of 1", "data.csv", ["name", "email"], process)
 runner.write("Step 1 of 1", "output.csv")
 ```
 
@@ -30,7 +30,7 @@ runner.write("Step 1 of 1", "output.csv")
 
 1. Opens the CSV and validates that all `required_headers` are present — raises immediately if any are missing
 2. Iterates every row with a `tqdm` progress bar labelled with `desc`
-3. Calls your `processor(row)` function — if it raises, that row is marked as an error and processing continues
+3. Calls your `validator(row)` function — if it raises, that row is marked as an error and processing continues
 4. Appends three columns to every row: `row number`, `row status`, and `message`
    - On success: `row status` and `message` are blank
    - On error: `row status = "error"`, `message = str(exception)`
@@ -51,15 +51,14 @@ runner.read(
     "Step 2 of 10",          # progress bar label — pass None to use the filename
     "data.csv",              # path to input CSV
     ["a", "b"],              # columns that must exist — raises ConfigError if missing
-    processor=my_func,       # optional: callable(row: dict) -> None
-    sample=100,              # optional: process only the first N rows
+    validator=my_func,       # optional: callable(row: dict) -> None
     enrich=True,             # optional: set False to skip row number/status/message columns
 )
 ```
 
-Reads and processes all rows. Results are stored in `runner.rows` as a list of dicts.
+Reads and processes all rows. Returns the rows as a `list[dict]` (same object as `runner.rows`).
 
-When `enrich=False`, processor exceptions are re-raised instead of captured.
+When `enrich=False`, validator exceptions are re-raised instead of captured.
 
 ### `runner.write()`
 

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "tha-csv-runner"
-version = "0.2.0"
+version = "0.2.2"
 description = "Run a function over every row of a CSV — with progress, header validation, and structured per-row errors."
 readme = "README.md"
 license = { text = "MIT" }

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/src/tha_csv_runner/__init__.py

@@ -3,5 +3,5 @@
 from .errors import ConfigError
 from .runner import ThaCSV
 
-__version__ = "0.2.0"
+__version__ = "0.2.2"
 __all__ = ["ConfigError", "ThaCSV"]

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/src/tha_csv_runner/runner.py

@@ -27,10 +27,9 @@ class ThaCSV:
         desc: str | None,
         input_path: str | Path,
         required_headers: list[str],
-        processor: Callable[[dict], None] | None = None,
-        sample: int | None = None,
+        validator: Callable[[dict], None] | None = None,
         enrich: bool = True,
-    ) -> None:
+    ) -> list[dict]:
         self._input_path = Path(input_path)
 
         with open(self._input_path, newline="", encoding="utf-8") as f:
@@ -42,9 +41,6 @@ class ThaCSV:
                 raise ConfigError(f"Missing required headers: {missing}")
             raw_rows = list(reader)
 
-        if sample is not None:
-            raw_rows = raw_rows[:sample]
-
         self.rows = []
         self._read = True
 
@@ -55,8 +51,8 @@ class ThaCSV:
             else:
                 enriched = dict(row)
             try:
-                if processor is not None:
-                    processor(enriched)
+                if validator is not None:
+                    validator(enriched)
             except Exception as exc:
                 if enrich:
                     enriched["row status"] = "error"
@@ -65,6 +61,8 @@ class ThaCSV:
                     raise
             self.rows.append(enriched)
 
+        return self.rows
+
     def write(
         self,
         desc: str | None,

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/tests/test_runner.py

@@ -23,6 +23,13 @@ def test_happy_path(simple_csv: Path) -> None:
     assert all(r["row status"] == "" for r in runner.rows)
 
 
+def test_read_returns_rows(simple_csv: Path) -> None:
+    runner = ThaCSV()
+    result = runner.read(None, simple_csv, ["name"])
+    assert result is runner.rows
+    assert len(result) == 3
+
+
 def test_row_number_injected(simple_csv: Path) -> None:
     runner = ThaCSV()
     runner.read(None, simple_csv, ["name"])
@@ -58,11 +65,6 @@ def test_missing_required_header_raises(simple_csv: Path) -> None:
         runner.read(None, simple_csv, ["id", "phone"])
 
 
-def test_sample_limits_rows(simple_csv: Path) -> None:
-    runner = ThaCSV()
-    runner.read(None, simple_csv, ["name"], sample=2)
-    assert len(runner.rows) == 2
-
 
 def test_original_columns_preserved(simple_csv: Path) -> None:
     runner = ThaCSV()
@@ -217,7 +219,7 @@ def test_enrich_false_preserves_original_columns(simple_csv: Path) -> None:
     assert runner.rows[0]["email"] == "alice@example.com"
 
 
-def test_enrich_false_processor_error_still_raises(simple_csv: Path) -> None:
+def test_enrich_false_validator_error_still_raises(simple_csv: Path) -> None:
     runner = ThaCSV()
     with pytest.raises(ValueError, match="Bob is not allowed"):
         runner.read(None, simple_csv, ["name"], fail_on_bob, enrich=False)

{tha_csv_runner-0.2.0 → tha_csv_runner-0.2.2}/uv.lock

@@ -308,7 +308,7 @@ wheels = [
 
 [[package]]
 name = "tha-csv-runner"
-version = "0.2.0"
+version = "0.2.2"
 source = { editable = "." }
 dependencies = [
     { name = "tqdm" },