dataframe-textual 2.4.2__py3-none-any.whl → 2.9.1__py3-none-any.whl

dataframe_textual/__main__.py

@@ -51,15 +51,34 @@ def cli() -> argparse.Namespace:
     )
     parser.add_argument("-E", "--ignore-errors", action="store_true", help="Ignore errors when reading CSV/TSV")
     parser.add_argument(
-        "-c", "--comment-prefix", nargs="?", const="#", help="Comment lines are skipped when reading CSV/TSV"
+        "-c",
+        "--comment-prefix",
+        metavar="PREFIX",
+        nargs="?",
+        const="#",
+        help="Comment lines starting with `PREFIX` are skipped when reading CSV/TSV",
     )
     parser.add_argument(
-        "-q", "--quote-char", nargs="?", const=None, default='"', help="Quote character for reading CSV/TSV"
+        "-q",
+        "--quote-char",
+        metavar="C",
+        nargs="?",
+        const=None,
+        default='"',
+        help="Use `C` as quote character for reading CSV/TSV",
     )
-    parser.add_argument("-l", "--skip-lines", type=int, default=0, help="Skip lines when reading CSV/TSV")
     parser.add_argument(
-        "-a", "--skip-rows-after-header", type=int, default=0, help="Skip rows after header when reading CSV/TSV"
+        "-L", "--skip-lines", metavar="N", type=int, default=0, help="Skip first N lines when reading CSV/TSV"
     )
+    parser.add_argument(
+        "-A",
+        "--skip-rows-after-header",
+        metavar="N",
+        type=int,
+        default=0,
+        help="Skip N rows after header when reading CSV/TSV",
+    )
+    parser.add_argument("-N", "--n-rows", metavar="N", type=int, help="Stop after reading N rows from CSV/TSV")
     parser.add_argument("-n", "--null", nargs="+", help="Values to interpret as null values when reading CSV/TSV")
 
     args = parser.parse_args()
@@ -98,6 +117,7 @@ def main() -> None:
         null_values=args.null,
         ignore_errors=args.ignore_errors,
         truncate_ragged_lines=args.truncate_ragged_lines,
+        n_rows=args.n_rows,
     )
     app = DataFrameViewer(*sources)
     app.run()

dataframe_textual/common.py

@@ -12,7 +12,7 @@ import polars as pl
 from rich.text import Text
 
 # Supported file formats
-SUPPORTED_FORMATS = ["tsv", "csv", "psv", "excel", "parquet", "json", "ndjson"]
+SUPPORTED_FORMATS = ["tsv", "csv", "psv", "xlsx", "xls", "parquet", "json", "ndjson"]
 
 
 # Boolean string mappings
@@ -485,6 +485,7 @@ def load_dataframe(
     null_values: list[str] | None = None,
     ignore_errors: bool = False,
     truncate_ragged_lines: bool = False,
+    n_rows: int | None = None,
 ) -> list[Source]:
     """Load DataFrames from file specifications.
 
@@ -502,6 +503,8 @@ def load_dataframe(
         skip_rows_after_header: Number of rows to skip after header. Defaults to 0.
         null_values: List of values to interpret as null when reading CSV/TSV files. Defaults to None.
         ignore_errors: Whether to ignore errors when reading CSV/TSV files. Defaults to False.
+        truncate_ragged_lines: Whether to truncate ragged lines when reading CSV/TSV files. Defaults to False.
+        n_rows: Number of rows to read from CSV/TSV files. Defaults to None (read all rows).
 
     Returns:
         List of `Source` objects.
@@ -531,8 +534,6 @@ def load_dataframe(
                 ext = Path(filename).with_suffix("").suffix.lower()
 
             fmt = ext.removeprefix(".")
-            if fmt in ("xls", "xlsx"):
-                fmt = "excel"
 
             # Default to TSV
             if not fmt or fmt not in SUPPORTED_FORMATS:
@@ -553,6 +554,7 @@ def load_dataframe(
                 null_values=null_values,
                 ignore_errors=ignore_errors,
                 truncate_ragged_lines=truncate_ragged_lines,
+                n_rows=n_rows,
             )
         )
 
@@ -637,6 +639,7 @@ def load_file(
     null_values: list[str] | None = None,
     ignore_errors: bool = False,
     truncate_ragged_lines: bool = False,
+    n_rows: int | None = None,
 ) -> list[Source]:
     """Load a single file.
 
@@ -662,6 +665,8 @@ def load_file(
         schema_overrides: Optional dictionary of column name to Polars data type to override inferred schema.
         null_values: List of values to interpret as null when reading CSV/TSV files. Defaults to None.
         ignore_errors: Whether to ignore errors when reading CSV/TSV files.
+        truncate_ragged_lines: Whether to truncate ragged lines when reading CSV/TSV files. Defaults to False.
+        n_rows: Number of rows to read from CSV/TSV files. Defaults to None (read all rows).
 
     Returns:
         List of `Source` objects.
@@ -686,9 +691,10 @@ def load_file(
             null_values=null_values,
             ignore_errors=ignore_errors,
             truncate_ragged_lines=truncate_ragged_lines,
+            n_rows=n_rows,
         )
         data.append(Source(lf, filename, filepath.stem))
-    elif file_format == "excel":
+    elif file_format in ("xlsx", "xls"):
         if first_sheet:
             # Read only the first sheet for multiple files
             lf = pl.read_excel(source).lazy()
@@ -742,6 +748,8 @@ def load_file(
             schema_overrides=schema_overrides,
             null_values=null_values,
             ignore_errors=ignore_errors,
+            truncate_ragged_lines=truncate_ragged_lines,
+            n_rows=n_rows,
         )
 
     return data