Francois9 pur for testing only

camelot/cli.py

@@ -290,13 +290,204 @@ def stream(c, *args, **kwargs):
     columns = list(kwargs["columns"])
     kwargs["columns"] = None if not columns else columns
 
-    margins = conf.pop('margins')
+    margins = conf.pop("margins")
 
     if margins is None:
         layout_kwargs = {}
     else:
-        layout_kwargs = {"char_margin": margins[0], "line_margin": margins[1], "word_margin": margins[2]}
-
+        layout_kwargs = {
+            "char_margin": margins[0],
+            "line_margin": margins[1],
+            "word_margin": margins[2],
+        }
+
+    if plot_type is not None:
+        if not _HAS_MPL:
+            raise ImportError("matplotlib is required for plotting.")
+    else:
+        if output is None:
+            raise click.UsageError("Please specify output file path using --output")
+        if f is None:
+            raise click.UsageError("Please specify output file format using --format")
+
+    tables = read_pdf(
+        filepath,
+        pages=pages,
+        flavor="stream",
+        suppress_stdout=quiet,
+        layout_kwargs=layout_kwargs,
+        **kwargs,
+    )
+    click.echo(f"Found {tables.n} tables")
+    if plot_type is not None:
+        for table in tables:
+            plot(table, kind=plot_type)
+            plt.show()
+    else:
+        tables.export(output, f=f, compress=compress)
+
+
+@cli.command("hybrid")
+@click.option(
+    "-R",
+    "--table_regions",
+    default=[],
+    multiple=True,
+    help="Page regions to analyze. Example: x1,y1,x2,y2"
+    " where x1, y1 -> left-top and x2, y2 -> right-bottom.",
+)
+@click.option(
+    "-T",
+    "--table_areas",
+    default=[],
+    multiple=True,
+    help="Table areas to process. Example: x1,y1,x2,y2"
+    " where x1, y1 -> left-top and x2, y2 -> right-bottom.",
+)
+@click.option(
+    "-C",
+    "--columns",
+    default=[],
+    multiple=True,
+    help="X coordinates of column separators.",
+)
+@click.option(
+    "-e",
+    "--edge_tol",
+    default=50,
+    help="Tolerance parameter" " for extending textedges vertically.",
+)
+@click.option(
+    "-r",
+    "--row_tol",
+    default=2,
+    help="Tolerance parameter" " used to combine text vertically, to generate rows.",
+)
+@click.option(
+    "-c",
+    "--column_tol",
+    default=0,
+    help="Tolerance parameter"
+    " used to combine text horizontally, to generate columns.",
+)
+@click.option(
+    "-plot",
+    "--plot_type",
+    type=click.Choice(["text", "grid", "contour", "textedge"]),
+    help="Plot elements found on PDF page for visual debugging.",
+)
+@click.argument("filepath", type=click.Path(exists=True))
+@pass_config
+def hybrid(c, *args, **kwargs):
+    """Use spaces between text to parse the table."""
+    conf = c.config
+    pages = conf.pop("pages")
+    output = conf.pop("output")
+    f = conf.pop("format")
+    compress = conf.pop("zip")
+    quiet = conf.pop("quiet")
+    plot_type = kwargs.pop("plot_type")
+    filepath = kwargs.pop("filepath")
+    kwargs.update(conf)
+
+    table_regions = list(kwargs["table_regions"])
+    kwargs["table_regions"] = None if not table_regions else table_regions
+    table_areas = list(kwargs["table_areas"])
+    kwargs["table_areas"] = None if not table_areas else table_areas
+    columns = list(kwargs["columns"])
+    kwargs["columns"] = None if not columns else columns
+
+    if plot_type is not None:
+        if not _HAS_MPL:
+            raise ImportError("matplotlib is required for plotting.")
+    else:
+        if output is None:
+            raise click.UsageError("Please specify output file path using --output")
+        if f is None:
+            raise click.UsageError("Please specify output file format using --format")
+
+    tables = read_pdf(
+        filepath, pages=pages, flavor="hybrid", suppress_stdout=quiet, **kwargs
+    )
+    click.echo(f"Found {tables.n} tables")
+    if plot_type is not None:
+        for table in tables:
+            plot(table, kind=plot_type)
+            plt.show()
+    else:
+        tables.export(output, f=f, compress=compress)
+
+
+@cli.command("network")
+@click.option(
+    "-R",
+    "--table_regions",
+    default=[],
+    multiple=True,
+    help="Page regions to analyze. Example: x1,y1,x2,y2"
+    " where x1, y1 -> left-top and x2, y2 -> right-bottom.",
+)
+@click.option(
+    "-T",
+    "--table_areas",
+    default=[],
+    multiple=True,
+    help="Table areas to process. Example: x1,y1,x2,y2"
+    " where x1, y1 -> left-top and x2, y2 -> right-bottom.",
+)
+@click.option(
+    "-C",
+    "--columns",
+    default=[],
+    multiple=True,
+    help="X coordinates of column separators.",
+)
+@click.option(
+    "-e",
+    "--edge_tol",
+    default=50,
+    help="Tolerance parameter" " for extending textedges vertically.",
+)
+@click.option(
+    "-r",
+    "--row_tol",
+    default=2,
+    help="Tolerance parameter" " used to combine text vertically, to generate rows.",
+)
+@click.option(
+    "-c",
+    "--column_tol",
+    default=0,
+    help="Tolerance parameter"
+    " used to combine text horizontally, to generate columns.",
+)
+@click.option(
+    "-plot",
+    "--plot_type",
+    type=click.Choice(["text", "grid", "contour", "textedge"]),
+    help="Plot elements found on PDF page for visual debugging.",
+)
+@click.argument("filepath", type=click.Path(exists=True))
+@pass_config
+def network(c, *args, **kwargs):
+    """Use spaces between text to parse the table."""
+    conf = c.config
+    pages = conf.pop("pages")
+    output = conf.pop("output")
+    f = conf.pop("format")
+    compress = conf.pop("zip")
+    quiet = conf.pop("quiet")
+    plot_type = kwargs.pop("plot_type")
+    filepath = kwargs.pop("filepath")
+    kwargs.update(conf)
+
+    table_regions = list(kwargs["table_regions"])
+    kwargs["table_regions"] = None if not table_regions else table_regions
+    table_areas = list(kwargs["table_areas"])
+    kwargs["table_areas"] = None if not table_areas else table_areas
+    columns = list(kwargs["columns"])
+    kwargs["columns"] = None if not columns else columns
+
     if plot_type is not None:
         if not _HAS_MPL:
             raise ImportError("matplotlib is required for plotting.")
@@ -307,7 +498,7 @@ def stream(c, *args, **kwargs):
             raise click.UsageError("Please specify output file format using --format")
 
     tables = read_pdf(
-        filepath, pages=pages, flavor="stream", suppress_stdout=quiet, layout_kwargs=layout_kwargs, **kwargs
+        filepath, pages=pages, flavor="network", suppress_stdout=quiet, **kwargs
     )
     click.echo(f"Found {tables.n} tables")
     if plot_type is not None: