dataframe-textual 2.2.3__py3-none-any.whl → 2.4.1__py3-none-any.whl

dataframe_textual/common.py

@@ -12,7 +12,7 @@ import polars as pl
 from rich.text import Text
 
 # Supported file formats
-SUPPORTED_FORMATS = {"tsv", "tab", "csv", "excel", "xlsx", "xls", "parquet", "json", "ndjson"}
+SUPPORTED_FORMATS = ["tsv", "csv", "psv", "excel", "parquet", "json", "ndjson"]
 
 
 # Boolean string mappings
@@ -529,7 +529,10 @@ def load_dataframe(
             ext = Path(filename).suffix.lower()
             if ext == ".gz":
                 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:
@@ -668,17 +671,11 @@ def load_file(
     filename = f"stdin.{file_format}" if isinstance(source, StringIO) else source
     filepath = Path(filename)
 
-    if not file_format:
-        ext = filepath.suffix.lower()
-        if ext == ".gz":
-            ext = Path(filename).with_suffix("").suffix.lower()
-        file_format = ext.removeprefix(".")
-
     # Load based on file format
-    if file_format in ("csv", "tsv"):
+    if file_format in ("csv", "tsv", "psv"):
         lf = pl.scan_csv(
             source,
-            separator="\t" if file_format == "tsv" else ",",
+            separator="\t" if file_format == "tsv" else ("|" if file_format == "psv" else ","),
             has_header=has_header,
             infer_schema=infer_schema,
             comment_prefix=comment_prefix,
@@ -691,7 +688,7 @@ def load_file(
             truncate_ragged_lines=truncate_ragged_lines,
         )
         data.append(Source(lf, filename, filepath.stem))
-    elif file_format in ("xlsx", "xls", "excel"):
+    elif file_format == "excel":
         if first_sheet:
             # Read only the first sheet for multiple files
             lf = pl.read_excel(source).lazy()

dataframe_textual/data_frame_table.py

@@ -1,5 +1,6 @@
 """DataFrameTable widget for displaying and interacting with Polars DataFrames."""
 
+import io
 import sys
 from collections import defaultdict, deque
 from dataclasses import dataclass
@@ -140,6 +141,7 @@ class DataFrameTable(DataTable):
         - **Ctrl+F** - 📜 Page down
         - **Ctrl+B** - 📜 Page up
         - **PgUp/PgDn** - 📜 Page up/down
+        - **&** - 📌 Mark current row as header
 
         ## ♻️ Undo/Redo/Reset
         - **u** - ↩️ Undo last action
@@ -248,6 +250,7 @@ class DataFrameTable(DataTable):
         ("comma", "toggle_thousand_separator", "Toggle thousand separator"),  # `,`
         ("underscore", "expand_column", "Expand column to full width"),  # `_`
         ("circumflex_accent", "toggle_rid", "Toggle internal row index"),  # `^`
+        ("ampersand", "set_cursor_row_as_header", "Set cursor row as the new header row"),  # `&`
         # Copy
         ("c", "copy_cell", "Copy cell to clipboard"),
         ("ctrl+c", "copy_column", "Copy column to clipboard"),
@@ -725,6 +728,10 @@ class DataFrameTable(DataTable):
         """Toggle the internal row index column visibility."""
         self.do_toggle_rid()
 
+    def action_set_cursor_row_as_header(self) -> None:
+        """Set cursor row as the new header row."""
+        self.do_set_cursor_row_as_header()
+
     def action_show_hidden_rows_columns(self) -> None:
         """Show all hidden rows/columns."""
         self.do_show_hidden_rows_columns()
@@ -1791,6 +1798,48 @@ class DataFrameTable(DataTable):
         # Recreate table for display
         self.setup_table()
 
+    def do_set_cursor_row_as_header(self) -> None:
+        """Set cursor row as the new header row."""
+        ridx = self.cursor_row_idx
+
+        # Get the new header values
+        new_header = list(self.df.row(ridx))
+        new_header[-1] = RID  # Ensure last column remains RID
+
+        # Handle duplicate column names by appending suffixes
+        seen = {}
+        for i, col in enumerate(new_header):
+            if col in seen:
+                seen[col] += 1
+                new_header[i] = f"{col}_{seen[col]}"
+            else:
+                seen[col] = 0
+
+        # Create a mapping of old column names to new column names
+        col_rename_map = {old_col: str(new_col) for old_col, new_col in zip(self.df.columns, new_header)}
+
+        # Add to history
+        self.add_history(f"Set row [$success]{ridx + 1}[/] as header", dirty=False)
+
+        # Rename columns in the dataframe
+        self.df = self.df.slice(ridx + 1).rename(col_rename_map)
+
+        # Write to string buffer
+        buffer = io.StringIO()
+        self.df.write_csv(buffer)
+
+        # Re-read with inferred schema to reset dtypes
+        buffer.seek(0)
+        self.df = pl.read_csv(buffer)
+
+        # Recreate table for display
+        self.setup_table()
+
+        # Move cursor to first column
+        self.move_cursor(row=ridx, column=0)
+
+        # self.notify(f"Set row [$success]{ridx + 1}[/] as header", title="Set Row as Header")
+
     def do_show_hidden_rows_columns(self) -> None:
         """Show all hidden rows/columns by recreating the table."""
         if not self.hidden_columns and self.df_view is None:

{dataframe_textual-2.2.3.dist-info → dataframe_textual-2.4.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframe-textual
-Version: 2.2.3
+Version: 2.4.1
 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
@@ -39,7 +39,7 @@ Description-Content-Type: text/markdown
 
 # DataFrame Textual
 
-A powerful, interactive terminal-based viewer/editor for CSV/TSV/Excel/Parquet/JSON/NDJSON built with Python, [Polars](https://pola.rs/), and [Textual](https://textual.textualize.io/). Inspired by [VisiData](https://www.visidata.org/), this tool provides smooth keyboard navigation, data manipulation, and a clean interface for exploring tabular data directly in terminal with multi-tab support for multiple files!
+A powerful, interactive terminal-based viewer/editor for CSV/TSV/PSV/Excel/Parquet/JSON/NDJSON built with Python, [Polars](https://pola.rs/), and [Textual](https://textual.textualize.io/). Inspired by [VisiData](https://www.visidata.org/), this tool provides smooth keyboard navigation, data manipulation, and a clean interface for exploring tabular data directly in terminal with multi-tab support for multiple files!
 
 ![Screenshot](https://raw.githubusercontent.com/need47/dataframe-textual/refs/heads/main/screenshot.png)
 
@@ -167,28 +167,31 @@ When multiple files are opened:
 ## Command Line Options
 
 ```
-usage: dv [-h] [-f {csv,excel,tsv,parquet,json,ndjson}] [-H] [-I] [-E] [-c COMMENT_PREFIX] [-q QUOTE_CHAR] [-l SKIP_LINES] [-a SKIP_ROWS_AFTER_HEADER] [-n NULL [NULL ...]] [files ...]
+usage: dv [-h] [-V] [-f {csv,json,excel,ndjson,psv,parquet,tsv}] [-H] [-I] [-t] [-E] [-c [COMMENT_PREFIX]] [-q [QUOTE_CHAR]] [-l SKIP_LINES] [-a SKIP_ROWS_AFTER_HEADER] [-n NULL [NULL ...]] [files ...]
 
-Interactive terminal based viewer/editor for tabular data (e.g., CSV/TSV/Excel).
+Interactive terminal based viewer/editor for tabular data (e.g., CSV/Excel).
 
 positional arguments:
-  files                 Input files (or read from stdin)
+  files                 Files to view (or read from stdin)
 
 options:
   -h, --help            show this help message and exit
-  -f, --format {csv,excel,tsv,parquet,json,ndjson}
-                        Specify the format of the input files
-  -H, --no-header       Specify that input files have no header row
-  -I, --no-inference   Do not infer data types when reading CSV/TSV
+  -V, --version         show program's version number and exit
+  -f, --format {csv,json,excel,ndjson,psv,parquet,tsv}
+                        Specify the format of the input files (csv, excel, tsv etc.)
+  -H, --no-header       Specify that input files have no header row when reading CSV/TSV
+  -I, --no-inference    Do not infer data types when reading CSV/TSV
+  -t, --truncate-ragged-lines
+                        Truncate ragged lines when reading CSV/TSV
   -E, --ignore-errors   Ignore errors when reading CSV/TSV
-  -c, --comment-prefix COMMENT_PREFIX
-                        Comment lines are skipped when reading CSV/TSV (default: skip none)
-  -q, --quote-char QUOTE_CHAR
-                        Quote character for reading CSV/TSV (default: "; use -q without argument value to disable)
+  -c, --comment-prefix [COMMENT_PREFIX]
+                        Comment lines are skipped when reading CSV/TSV
+  -q, --quote-char [QUOTE_CHAR]
+                        Quote character for reading CSV/TSV
   -l, --skip-lines SKIP_LINES
-                        Skip lines when reading CSV/TSV (default: 0)
+                        Skip lines when reading CSV/TSV
   -a, --skip-rows-after-header SKIP_ROWS_AFTER_HEADER
-                        Skip rows after header when reading CSV/TSV (default: 0)
+                        Skip rows after header when reading CSV/TSV
   -n, --null NULL [NULL ...]
                         Values to interpret as null values when reading CSV/TSV
 ```
@@ -302,6 +305,7 @@ zcat compressed_data.csv.gz | dv -f csv
 | `_` (underscore) | Toggle column full width |
 | `z` | Freeze rows and columns |
 | `,` | Toggle thousand separator for numeric display |
+| `&` | Set current row as the new header row | 
 | `h` | Hide current column |
 | `H` | Show all hidden rows/columns |
 
@@ -696,7 +700,7 @@ Press `,` to toggle thousand separator formatting for numeric data:
 
 ### 15. Save File
 
-Press `Ctrl+S` to save filtered, edited, or sorted data back to file
+Press `Ctrl+S` to save filtered, edited, or sorted data back to file. The output format is automatically determined by the file extension, making it easy to convert between different formats (e.g., CSV to TSV).
 
 ### 16. Undo/Redo/Reset
 

{dataframe_textual-2.2.3.dist-info → dataframe_textual-2.4.1.dist-info}/RECORD

@@ -1,14 +1,14 @@
 dataframe_textual/__init__.py,sha256=E53fW1spQRA4jW9grxSqPEmoe9zofzr6twdveMbt_W8,1310
 dataframe_textual/__main__.py,sha256=xXeUA2EqVhufPkTbvv6MOCt3_ESHBH3PsCE--07a0ww,3613
-dataframe_textual/common.py,sha256=dF6trD4C60cybtOwAaeILAKXdBh6nltnkyBrh2twXo8,28632
+dataframe_textual/common.py,sha256=8Fqwuco7z4p_3GDCF7Gp8SYGUz24Sncpc457FCyMMWk,28516
 dataframe_textual/data_frame_help_panel.py,sha256=UEtj64XsVRdtLzuwOaITfoEQUkAfwFuvpr5Npip5WHs,3381
-dataframe_textual/data_frame_table.py,sha256=OPi9TCW_Xjj3AZJhp6bIwe538xkpC4TSU0aRlLGgMWc,149673
+dataframe_textual/data_frame_table.py,sha256=vvXgM-BDHKLCHzue3JJ5O7OKIlMj3w8WyJCVe4eAoeE,151405
 dataframe_textual/data_frame_viewer.py,sha256=aUjIk9BWYKyMG87PirFxR79iNLzkEcZ-I5XVnXwDEnU,23284
 dataframe_textual/sql_screen.py,sha256=P3j1Fv45NIKEYo9adb7NPod54FaU-djFIvCUMMHbvjY,7534
 dataframe_textual/table_screen.py,sha256=XPzJI6FXjwnxtQSMTmluygwkYM-0-Lx3v9o-MuL6bMg,19071
 dataframe_textual/yes_no_screen.py,sha256=NI7Zt3rETDWYiT5CH_FDy7sIWkZ7d7LquaZZbX79b2g,26400
-dataframe_textual-2.2.3.dist-info/METADATA,sha256=wvRLdCrQkWk-P53o-7cdSLqbdLCUvaJgLXZAXqvNi4o,29160
-dataframe_textual-2.2.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-dataframe_textual-2.2.3.dist-info/entry_points.txt,sha256=R_GoooOxcq6ab4RaHiVoZ4zrZJ-phMcGmlL2rwqncW8,107
-dataframe_textual-2.2.3.dist-info/licenses/LICENSE,sha256=AVTg0gk1X-LHI-nnHlAMDQetrwuDZK4eypgSMDO46Yc,1069
-dataframe_textual-2.2.3.dist-info/RECORD,,
+dataframe_textual-2.4.1.dist-info/METADATA,sha256=Jj-BukRTx4rrxFOD1c79kS7saUiIziHe7pNPAK_dnvI,29482
+dataframe_textual-2.4.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+dataframe_textual-2.4.1.dist-info/entry_points.txt,sha256=R_GoooOxcq6ab4RaHiVoZ4zrZJ-phMcGmlL2rwqncW8,107
+dataframe_textual-2.4.1.dist-info/licenses/LICENSE,sha256=AVTg0gk1X-LHI-nnHlAMDQetrwuDZK4eypgSMDO46Yc,1069
+dataframe_textual-2.4.1.dist-info/RECORD,,