2.9.049

.github/README.md

@@ -99,7 +99,7 @@ To stop playing press Ctrl+C in either the terminal or mpv
 <details><summary>List all subcommands</summary>
 
     $ library
-    library (v2.9.048; 86 subcommands)
+    library (v2.9.049; 86 subcommands)
 
     Create database subcommands:
     ╭─────────────────┬──────────────────────────────────────────╮

tests/tablefiles/test_markdown_tables.py

@@ -40,3 +40,9 @@ def test_lb_markdown_tables_transpose(mock_stdin, assert_unchanged, capsys):
         lb(["markdown-tables", "--from-json", "--transpose", "--to-json"])
     captured = capsys.readouterr().out
     assert_unchanged([json.loads(s) for s in captured.splitlines()])
+
+
+def test_lb_markdown_tables_skip_header(assert_unchanged, capsys):
+    lb(["markdown-tables", "--skip-header", "--start-row=1", "--to-json", "tests/data/test.xlsx"])
+    captured = capsys.readouterr().out
+    assert_unchanged([json.loads(s) for s in captured.splitlines()])

tests/tablefiles/test_markdown_tables/test_lb_markdown_tables_skip_header.yml

@@ -0,0 +1,8 @@
+- column0: 0
+  column1: 1
+  column2: 3
+  column3: 5
+- column0: 1
+  column1: 2
+  column2: 4
+  column3: 6

xklb/__main__.py

@@ -5,7 +5,7 @@
 from xklb.utils import argparse_utils, iterables
 from xklb.utils.log_utils import log
 
-__version__ = "2.9.048"
+__version__ = "2.9.049"
 
 progs = {
     "Create database subcommands": {

xklb/createdb/tables_add.py

@@ -47,6 +47,7 @@ def table_add(args, path):
         mimetype=args.mimetype,
         join_tables=args.join_tables,
         transpose=args.transpose,
+        skip_headers=args.skip_headers,
     )
     for i, df in enumerate(dfs):
         if args.table_rename:

xklb/tablefiles/columns.py

@@ -36,6 +36,7 @@ def file_columns(args, path):
         mimetype=args.mimetype,
         join_tables=args.join_tables,
         transpose=args.transpose,
+        skip_headers=args.skip_headers,
     ):
         df_name = df.name
 

xklb/tablefiles/eda.py

@@ -190,6 +190,7 @@ def file_eda(args, path):
         mimetype=args.mimetype,
         join_tables=args.join_tables,
         transpose=args.transpose,
+        skip_headers=args.skip_headers,
     )
     if getattr(args, "repl", False):
         breakpoint()

xklb/tablefiles/markdown_tables.py

@@ -32,6 +32,7 @@ def file_markdown(args, path):
         mimetype=args.mimetype,
         join_tables=args.join_tables,
         transpose=args.transpose,
+        skip_headers=args.skip_headers,
     ):
         if getattr(args, "repl", False):
             breakpoint()

xklb/tablefiles/mcda.py

@@ -247,6 +247,7 @@ def file_mcda(args, path):
         mimetype=args.mimetype,
         join_tables=args.join_tables,
         transpose=args.transpose,
+        skip_headers=args.skip_headers,
     )
 
     for df in dfs:

xklb/utils/arggroups.py

@@ -1323,6 +1323,7 @@ def table_like(parent_parser):
     parser.add_argument("--table-name", "--table", "-t", help="Load from a specific table by name")
     parser.add_argument("--table-index", type=int, help="Load from a specific table by index")
     parser.add_argument("--table-rename", "--rename-table", "--as-table-name", help="Load to specific table by name")
+    parser.add_argument("--skip-headers", "--ignore-headers", action="store_true")
     parser.add_argument("--start-row", "--skiprows", type=int, default=None, help="Skip reading N rows")
     parser.add_argument(
         "--end-row",

xklb/utils/file_utils.py

@@ -466,6 +466,7 @@ def read_file_to_dataframes(
     mimetype=None,
     join_tables=False,
     transpose=False,
+    skip_headers=False,
 ):
     import pandas as pd
 
@@ -508,7 +509,13 @@ def read_file_to_dataframes(
         "excel spreadsheet subheader",
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
     ):
-        excel_data = pd.read_excel(path, sheet_name=table_name or table_index, nrows=end_row, skiprows=start_row)
+        excel_data = pd.read_excel(
+            path,
+            sheet_name=table_name or table_index,
+            nrows=end_row,
+            skiprows=start_row,
+            header=None if skip_headers else 0,
+        )
         dfs = []
         if isinstance(excel_data, pd.DataFrame):
             worksheet_names = excel_data.index.levels[0]  # type: ignore
@@ -549,21 +556,43 @@ def read_file_to_dataframes(
         "csv",
         "text/csv",
     ):
-        dfs = [pd.read_csv(path, nrows=end_row, skiprows=start_row or 0, encoding=encoding)]
+        dfs = [
+            pd.read_csv(
+                path, nrows=end_row, skiprows=start_row or 0, encoding=encoding, header=None if skip_headers else 0
+            )
+        ]
     elif mimetype in (
         "plain",
         "plaintext",
         "wsv",
         "text/wsv",
         "text/whitespace-separated-values",
     ):
-        dfs = [pd.read_csv(path, delim_whitespace=True, nrows=end_row, skiprows=start_row or 0, encoding=encoding)]
+        dfs = [
+            pd.read_csv(
+                path,
+                delim_whitespace=True,
+                nrows=end_row,
+                skiprows=start_row or 0,
+                encoding=encoding,
+                header=None if skip_headers else 0,
+            )
+        ]
     elif mimetype in (
         "tsv",
         "text/tsv",
         "text/tab-separated-values",
     ):
-        dfs = [pd.read_csv(path, delimiter="\t", nrows=end_row, skiprows=start_row or 0, encoding=encoding)]
+        dfs = [
+            pd.read_csv(
+                path,
+                delimiter="\t",
+                nrows=end_row,
+                skiprows=start_row or 0,
+                encoding=encoding,
+                header=None if skip_headers else 0,
+            )
+        ]
     elif mimetype in ("parq", "parquet", "application/parquet"):
         dfs = [pd.read_parquet(path)]
     elif mimetype in ("pkl", "pickle", "application/octet-stream"):
@@ -618,6 +647,9 @@ def read_file_to_dataframes(
         if not hasattr(df, "name"):
             df.name = str(table_index_as_name)
 
+    if skip_headers:
+        df.columns = [f"column{i}" for i in range(len(df.columns))]
+
     if transpose:
 
         def t(df):