dataframe-textual 1.1.0__py3-none-any.whl → 1.1.4__py3-none-any.whl

dataframe_textual/__init__.py

@@ -2,7 +2,7 @@
 
 from .data_frame_help_panel import DataFrameHelpPanel
 from .data_frame_table import DataFrameTable, History
-from .data_frame_viewer import DataFrameViewer, _load_dataframe
+from .data_frame_viewer import DataFrameViewer
 from .table_screen import FrequencyScreen, RowDetailScreen, TableScreen
 from .yes_no_screen import (
     ConfirmScreen,
@@ -31,5 +31,4 @@ __all__ = [
     "FilterScreen",
     "FreezeScreen",
     "OpenFileScreen",
-    "_load_dataframe",
 ]

dataframe_textual/__main__.py

@@ -4,6 +4,7 @@ import argparse
 import sys
 from pathlib import Path
 
+from .common import load_dataframe
 from .data_frame_viewer import DataFrameViewer
 
 SUPPORTED_FORMATS = ["csv", "excel", "tsv", "parquet", "json", "ndjson"]
@@ -22,13 +23,14 @@ def main() -> None:
         SystemExit: If invalid arguments are provided or required files are missing.
     """
     parser = argparse.ArgumentParser(
+        prog="dv",
         description="Interactive terminal based viewer/editor for tabular data (e.g., CSV/Excel).",
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="Examples:\n"
-        "  dataframe-textual data.csv\n"
-        "  dataframe-textual file1.csv file2.csv file3.csv\n"
-        "  dataframe-textual data.xlsx  (opens all sheets in tabs)\n"
-        "  cat data.csv | dataframe-textual --format csv\n",
+        "  %(prog)s data.csv\n"
+        "  %(prog)s file1.csv file2.csv file3.csv\n"
+        "  %(prog)s data.xlsx  (opens each sheet in separate tab)\n"
+        "  cat data.csv | %(prog)s --format csv\n",
     )
     parser.add_argument("files", nargs="*", help="Files to view (or read from stdin)")
     parser.add_argument(
@@ -57,7 +59,8 @@ def main() -> None:
         parser.print_help()
         sys.exit(1)
 
-    app = DataFrameViewer(*filenames, file_format=args.format, has_header=not args.no_header)
+    sources = load_dataframe(filenames, file_format=args.format, has_header=not args.no_header)
+    app = DataFrameViewer(*sources)
     app.run()
 
 

dataframe_textual/common.py

@@ -1,7 +1,9 @@
 """Common utilities and constants for dataframe_viewer."""
 
 import re
+import sys
 from dataclasses import dataclass
+from pathlib import Path
 from typing import Any
 
 import polars as pl
@@ -338,3 +340,122 @@ def validate_expr(term: str, df: pl.DataFrame, current_col_idx: int) -> pl.Expr
             raise ValueError(f"Failed to evaluate expression `{expr_str}`: {e}") from e
     except Exception as ve:
         raise ValueError(f"Failed to validate expression `{term}`: {ve}") from ve
+
+
+def load_dataframe(
+    filenames: list[str], file_format: str | None = None, has_header: bool = True
+) -> list[tuple[pl.LazyFrame, str, str]]:
+    """Load DataFrames from file specifications.
+
+    Handles loading from multiple files, single files, or stdin. For Excel files,
+    loads all sheets as separate entries. For other formats, loads as single file.
+
+    Args:
+        filenames: List of filenames to load. If single filename is "-", read from stdin.
+        file_format: Optional format specifier for input files (e.g., 'csv', 'excel').
+        has_header: Whether the input files have a header row. Defaults to True.
+
+    Returns:
+        List of tuples of (LazyFrame, filename, tabname) ready for display.
+    """
+    sources = []
+
+    prefix_sheet = len(filenames) > 1
+
+    for filename in filenames:
+        sources.extend(load_file(filename, prefix_sheet=prefix_sheet, file_format=file_format, has_header=has_header))
+    return sources
+
+
+def load_file(
+    filename: str,
+    first_sheet: bool = False,
+    prefix_sheet: bool = False,
+    file_format: str | None = None,
+    has_header: bool = True,
+) -> list[tuple[pl.LazyFrame, str, str]]:
+    """Load a single file and return list of sources.
+
+    For Excel files, when `first_sheet` is True, returns only the first sheet. Otherwise, returns one entry per sheet.
+    For other files or multiple files, returns one entry per file.
+
+    Args:
+        filename: Path to file to load.
+        first_sheet: If True, only load first sheet for Excel files. Defaults to False.
+        prefix_sheet: If True, prefix filename to sheet name as the tab name for Excel files. Defaults to False.
+        file_format: Optional format specifier (i.e., 'csv', 'excel', 'tsv', 'parquet', 'json', 'ndjson') for input files.
+                     By default, infers from file extension.
+        has_header: Whether the input files have a header row. Defaults to True.
+
+    Returns:
+        List of tuples of (LazyFrame, filename, tabname).
+    """
+    sources = []
+
+    if filename == "-":
+        import os
+        from io import StringIO
+
+        # Read from stdin into memory first (stdin is not seekable)
+        stdin_data = sys.stdin.read()
+        lf = pl.scan_csv(StringIO(stdin_data), has_header=has_header, separator="," if file_format == "csv" else "\t")
+
+        # Reopen stdin to /dev/tty for proper terminal interaction
+        try:
+            tty = open("/dev/tty")
+            os.dup2(tty.fileno(), sys.stdin.fileno())
+        except (OSError, FileNotFoundError):
+            pass
+
+        sources.append((lf, f"stdin.{file_format}" if file_format else "stdin", "stdin"))
+        return sources
+
+    filepath = Path(filename)
+
+    if file_format == "csv":
+        lf = pl.scan_csv(filename, has_header=has_header)
+        sources.append((lf, filename, filepath.stem))
+    elif file_format == "excel":
+        if first_sheet:
+            # Read only the first sheet for multiple files
+            lf = pl.read_excel(filename).lazy()
+            sources.append((lf, filename, filepath.stem))
+        else:
+            # For single file, expand all sheets
+            sheets = pl.read_excel(filename, sheet_id=0)
+            for sheet_name, df in sheets.items():
+                tabname = f"{filepath.stem}_{sheet_name}" if prefix_sheet else sheet_name
+                sources.append((df.lazy(), filename, tabname))
+    elif file_format == "tsv":
+        lf = pl.scan_csv(filename, has_header=has_header, separator="\t")
+        sources.append((lf, filename, filepath.stem))
+    elif file_format == "parquet":
+        lf = pl.scan_parquet(filename)
+        sources.append((lf, filename, filepath.stem))
+    elif file_format == "json":
+        df = pl.read_json(filename)
+        sources.append((df, filename, filepath.stem))
+    elif file_format == "ndjson":
+        lf = pl.scan_ndjson(filename)
+        sources.append((lf, filename, filepath.stem))
+    else:
+        ext = filepath.suffix.lower()
+        if ext == ".csv":
+            file_format = "csv"
+        elif ext in (".xlsx", ".xls"):
+            file_format = "excel"
+        elif ext in (".tsv", ".tab"):
+            file_format = "tsv"
+        elif ext == ".parquet":
+            file_format = "parquet"
+        elif ext == ".json":
+            file_format = "json"
+        elif ext == ".ndjson":
+            file_format = "ndjson"
+        else:
+            # Default to TSV
+            file_format = "tsv"
+
+        sources.extend(load_file(filename, first_sheet, prefix_sheet, file_format, has_header))
+
+    return sources

dataframe_textual/data_frame_viewer.py

@@ -1,7 +1,6 @@
 """DataFrame Viewer application and utilities."""
 
 import os
-import sys
 from functools import partial
 from pathlib import Path
 from textwrap import dedent
@@ -13,7 +12,7 @@ from textual.theme import BUILTIN_THEMES
 from textual.widgets import TabbedContent, TabPane
 from textual.widgets.tabbed_content import ContentTab, ContentTabs
 
-from .common import get_next_item
+from .common import get_next_item, load_file
 from .data_frame_help_panel import DataFrameHelpPanel
 from .data_frame_table import DataFrameTable
 from .yes_no_screen import OpenFileScreen, SaveFileScreen
@@ -79,21 +78,20 @@ class DataFrameViewer(App):
         }
     """
 
-    def __init__(self, *filenames: str, file_format: str | None = None, has_header: bool = True) -> None:
+    def __init__(self, *sources: str) -> None:
         """Initialize the DataFrame Viewer application.
 
-        Loads dataframes from provided filenames and prepares the tabbed interface.
+        Loads data from provided sources and prepares the tabbed interface.
 
         Args:
-            *filenames: Variable number of file paths to load (CSV, Excel, Parquet, etc).
-            file_format: Optional format specifier for input files (e.g., 'csv', 'excel').
-            has_header: Whether the input files have a header row. Defaults to True.
+            sources: sources to load dataframes from, each as a tuple of
+                     (DataFrame | LazyFrame, filename, tabname).
 
         Returns:
             None
         """
         super().__init__()
-        self.sources = _load_dataframe(filenames, file_format, has_header=has_header)
+        self.sources = sources
         self.tabs: dict[TabPane, DataFrameTable] = {}
         self.help_panel = None
 
@@ -111,12 +109,18 @@ class DataFrameViewer(App):
         with self.tabbed:
             seen_names = set()
             for idx, (df, filename, tabname) in enumerate(self.sources, start=1):
+                tab_id = f"tab_{idx}"
+
+                if not tabname:
+                    tabname = Path(filename).stem or tab_id
+
                 # Ensure unique tab names
-                if tabname in seen_names:
-                    tabname = f"{tabname}_{idx}"
+                counter = 1
+                while tabname in seen_names:
+                    tabname = f"{tabname}_{counter}"
+                    counter += 1
                 seen_names.add(tabname)
 
-                tab_id = f"tab_{idx}"
                 try:
                     table = DataFrameTable(df, filename, name=tabname, id=tab_id, zebra_stripes=True)
                     tab = TabPane(tabname, table, name=tabname, id=tab_id)
@@ -300,7 +304,7 @@ class DataFrameViewer(App):
         if filename and os.path.exists(filename):
             try:
                 n_tab = 0
-                for lf, filename, tabname in _load_file(filename, prefix_sheet=True):
+                for lf, filename, tabname in load_file(filename, prefix_sheet=True):
                     self._add_tab(lf.collect(), filename, tabname)
                     n_tab += 1
                 self.notify(f"Added [$accent]{n_tab}[/] tab(s) for [$success]{filename}[/]", title="Open")
@@ -368,105 +372,3 @@ class DataFrameViewer(App):
                     self.notify(f"Closed tab [$success]{active_pane.name}[/]", title="Close")
         except NoMatches:
             pass
-
-
-def _load_dataframe(
-    filenames: list[str], file_format: str | None = None, has_header: bool = True
-) -> list[tuple[pl.LazyFrame, str, str]]:
-    """Load DataFrames from file specifications.
-
-    Handles loading from multiple files, single files, or stdin. For Excel files,
-    loads all sheets as separate entries. For other formats, loads as single file.
-
-    Args:
-        filenames: List of filenames to load. If single filename is "-", read from stdin.
-        file_format: Optional format specifier for input files (e.g., 'csv', 'excel').
-        has_header: Whether the input files have a header row. Defaults to True.
-
-    Returns:
-        List of tuples of (LazyFrame, filename, tabname) ready for display.
-    """
-    sources = []
-
-    prefix_sheet = len(filenames) > 1
-
-    for filename in filenames:
-        sources.extend(_load_file(filename, prefix_sheet=prefix_sheet, file_format=file_format, has_header=has_header))
-    return sources
-
-
-def _load_file(
-    filename: str,
-    first_sheet: bool = False,
-    prefix_sheet: bool = False,
-    file_format: str | None = None,
-    has_header: bool = True,
-) -> list[tuple[pl.LazyFrame, str, str]]:
-    """Load a single file and return list of sources.
-
-    For Excel files, when `first_sheet` is True, returns only the first sheet. Otherwise, returns one entry per sheet.
-    For other files or multiple files, returns one entry per file.
-
-    Args:
-        filename: Path to file to load.
-        first_sheet: If True, only load first sheet for Excel files. Defaults to False.
-        prefix_sheet: If True, prefix filename to sheet name as the tab name for Excel files. Defaults to False.
-        file_format: Optional format specifier for input files (e.g., 'csv', 'excel', 'tsv', 'parquet', 'json', 'ndjson').
-
-    Returns:
-        List of tuples of (LazyFrame, filename, tabname).
-    """
-    sources = []
-
-    if filename == "-":
-        from io import StringIO
-
-        # Read from stdin into memory first (stdin is not seekable)
-        stdin_data = sys.stdin.read()
-        lf = pl.scan_csv(StringIO(stdin_data), has_header=has_header, separator="," if file_format == "csv" else "\t")
-
-        # Reopen stdin to /dev/tty for proper terminal interaction
-        try:
-            tty = open("/dev/tty")
-            os.dup2(tty.fileno(), sys.stdin.fileno())
-        except (OSError, FileNotFoundError):
-            pass
-
-        sources.append((lf, "stdin.tsv" if file_format == "tsv" else "stdin.csv", "stdin"))
-        return sources
-
-    filepath = Path(filename)
-    ext = filepath.suffix.lower()
-
-    if file_format == "csv" or ext == ".csv":
-        lf = pl.scan_csv(filename, has_header=has_header)
-        sources.append((lf, filename, filepath.stem))
-    elif file_format == "excel" or ext in (".xlsx", ".xls"):
-        if first_sheet:
-            # Read only the first sheet for multiple files
-            lf = pl.read_excel(filename).lazy()
-            sources.append((lf, filename, filepath.stem))
-        else:
-            # For single file, expand all sheets
-            sheets = pl.read_excel(filename, sheet_id=0)
-            for sheet_name, df in sheets.items():
-                tabname = f"{filepath.stem}_{sheet_name}" if prefix_sheet else sheet_name
-                sources.append((df.lazy(), filename, tabname))
-    elif file_format == "tsv" or ext in (".tsv", ".tab"):
-        lf = pl.scan_csv(filename, has_header=has_header, separator="\t")
-        sources.append((lf, filename, filepath.stem))
-    elif file_format == "parquet" or ext == ".parquet":
-        lf = pl.scan_parquet(filename)
-        sources.append((lf, filename, filepath.stem))
-    elif file_format == "json" or ext == ".json":
-        df = pl.read_json(filename)
-        sources.append((df, filename, filepath.stem))
-    elif file_format == "ndjson" or ext == ".ndjson":
-        lf = pl.scan_ndjson(filename)
-        sources.append((lf, filename, filepath.stem))
-    else:
-        # Treat other formats as TSV
-        lf = pl.scan_csv(filename, has_header=has_header, separator="\t")
-        sources.append((lf, filename, filepath.stem))
-
-    return sources

{dataframe_textual-1.1.0.dist-info → dataframe_textual-1.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframe-textual
-Version: 1.1.0
+Version: 1.1.4
 Summary: Interactive terminal viewer/editor for tabular data
 Project-URL: Homepage, https://github.com/need47/dataframe-textual
 Project-URL: Repository, https://github.com/need47/dataframe-textual.git
@@ -92,6 +92,7 @@ uvx https://github.com/need47/dataframe-textual.git <csvfile>
 
 # Clone or download the project
 cd dataframe-textual
+uv sync --extra excel  # with Excel support
 
 # Run directly with uv
 uv run dv <csv_file>

dataframe_textual-1.1.4.dist-info/RECORD

@@ -0,0 +1,13 @@
+dataframe_textual/__init__.py,sha256=IFPb8RMUgghw0eRomehkkC684Iny_gs1VkiZMQ5ZpFk,813
+dataframe_textual/__main__.py,sha256=hgjKLT3ggGxVVeRBunkArTy7PTqOHVJUf3fsH4P5dfU,2146
+dataframe_textual/common.py,sha256=q4bXS7oiJAsdcMEfHkPm5-e8SlfcwCBNhFN9TinQqV0,16171
+dataframe_textual/data_frame_help_panel.py,sha256=XgKGEPJr2hnDWpZ5mavLRcBSPa9cvrXdzVUGFQavXm4,3353
+dataframe_textual/data_frame_table.py,sha256=mOm0pzuN61N01KXi_II6Ld4-NqVYYdiKfzukDMlJpxw,102644
+dataframe_textual/data_frame_viewer.py,sha256=4mV3k7MNTf9TKBmGJ8fDx7itA1vo4qSmaWpvZozwfjs,12987
+dataframe_textual/table_screen.py,sha256=vSevLh944xBTIYVcokABCfSUi84s9gclizx6eDmxyFY,17585
+dataframe_textual/yes_no_screen.py,sha256=vyUKMBbbwgt5At1U430eLg3WbJvqUNoz2GpvdnMd7q0,22921
+dataframe_textual-1.1.4.dist-info/METADATA,sha256=GKyTQtMDbIdgJD6zv9WIex6Oq4SvmYfNH3xDw4mZwb4,25422
+dataframe_textual-1.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+dataframe_textual-1.1.4.dist-info/entry_points.txt,sha256=Z0XKp1ACvmbJymekkxt-C81I0OoInksr5Ib0w2OT_a4,55
+dataframe_textual-1.1.4.dist-info/licenses/LICENSE,sha256=AVTg0gk1X-LHI-nnHlAMDQetrwuDZK4eypgSMDO46Yc,1069
+dataframe_textual-1.1.4.dist-info/RECORD,,

dataframe_textual-1.1.0.dist-info/RECORD

@@ -1,13 +0,0 @@
-dataframe_textual/__init__.py,sha256=uzB3bjlbm8JbsjxEgwqvPcYERktm3F9d9Op_6cWJ1sk,853
-dataframe_textual/__main__.py,sha256=ANe7s2SKO53ksFg-0VrCT2GRCG48wDSAZsLrWvoQwmQ,2082
-dataframe_textual/common.py,sha256=JVGl5ImbC8h9-nodcGZCyNmRcO2VlCF1-yo8Zg8uD90,11583
-dataframe_textual/data_frame_help_panel.py,sha256=XgKGEPJr2hnDWpZ5mavLRcBSPa9cvrXdzVUGFQavXm4,3353
-dataframe_textual/data_frame_table.py,sha256=mOm0pzuN61N01KXi_II6Ld4-NqVYYdiKfzukDMlJpxw,102644
-dataframe_textual/data_frame_viewer.py,sha256=9vUBdIgSoOf4fdDtI4sAPY6cF1tFdsXwpWatyDsuXh0,17196
-dataframe_textual/table_screen.py,sha256=vSevLh944xBTIYVcokABCfSUi84s9gclizx6eDmxyFY,17585
-dataframe_textual/yes_no_screen.py,sha256=vyUKMBbbwgt5At1U430eLg3WbJvqUNoz2GpvdnMd7q0,22921
-dataframe_textual-1.1.0.dist-info/METADATA,sha256=FvSPyXMtELpoIrqfXhzlUkPRb91-6GM16NDwIr-q24g,25378
-dataframe_textual-1.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-dataframe_textual-1.1.0.dist-info/entry_points.txt,sha256=Z0XKp1ACvmbJymekkxt-C81I0OoInksr5Ib0w2OT_a4,55
-dataframe_textual-1.1.0.dist-info/licenses/LICENSE,sha256=AVTg0gk1X-LHI-nnHlAMDQetrwuDZK4eypgSMDO46Yc,1069
-dataframe_textual-1.1.0.dist-info/RECORD,,