Merge branch 'main' into fix_version_for_cli

Author: bosd

.github/workflows/release.yml

@@ -56,7 +56,7 @@ jobs:
 
       - name: Publish package on PyPI
         if: steps.check-version.outputs.tag
-        uses: pypa/gh-action-pypi-publish@v1.11.0
+        uses: pypa/gh-action-pypi-publish@v1.12.2
         with:
           user: __token__
           password: ${{ secrets.FLIT_PASSWORD }}

HISTORY.md

@@ -19,8 +19,8 @@ Or follow the example below.
 You can check out the PDF used in this example [here](https://github.com/py-pdf/pypdf_table_extraction/blob/main/docs/_static/pdf/foo.pdf).
 
 ```python3
->>> import camelot
->>> tables = camelot.read_pdf('foo.pdf')
+>>> import pypdf_table_extraction
+>>> tables = pypdf_table_extraction.read_pdf('foo.pdf')
 >>> tables
 <TableList n=1>
 >>> tables.export('foo.csv', f='csv', compress=True) # json, excel, html, markdown, sqlite
@@ -50,6 +50,8 @@ pypdf_table_extraction also comes packaged with a [command-line interface](https
 
 Refer to the [QuickStart Guide](https://github.com/py-pdf/pypdf_table_extraction/blob/main/docs/user/quickstart.rst#quickstart) to quickly get started with pypdf_table_extraction, extract tables from PDFs and explore some basic options.
 
+**Tip:** Visit the `parser-comparison-notebook` to get an overview of all the packed parsers and their features. [![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/py-pdf/pypdf_table_extraction/blob/main/examples/parser-comparison-notebook.ipynb)
+
 **Note:** pypdf_table_extraction only works with text-based PDFs and not scanned documents. (As Tabula [explains](https://github.com/tabulapdf/tabula#why-tabula), "If you can click and drag to select text in your table in a PDF viewer, then your PDF is text-based".)
 
 You can check out some frequently asked questions [here](https://pypdf-table-extraction.readthedocs.io/en/latest/user/faq.html).
@@ -77,7 +79,7 @@ conda install -c conda-forge pypdf-table-extraction
 After [installing the dependencies](https://pypdf-table-extraction.readthedocs.io/en/latest/user/install-deps.html) ([tk](https://packages.ubuntu.com/bionic/python/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can also just use pip to install pypdf_table_extraction:
 
 ```bash
-pip install pypdf-table-extraction[base]
+pip install pypdf-table-extraction
 ```
 
 ### From the source code
@@ -91,8 +93,8 @@ git clone https://github.com/py-pdf/pypdf_table_extraction.git
 and install using pip:
 
 ```
-cd camelot
-pip install ".[base]"
+cd pypdf_table_extraction
+pip install "."
 ```
 
 ## Documentation

README.md

@@ -38,7 +38,9 @@ def set_config(self, key, value):
 
 @click.group(name="camelot")
 @click.version_option(version=__version__)
-@click.option("-q", "--quiet", is_flag=False, help="Suppress logs and warnings.")
+@click.option(
+    "-q", "--quiet", is_flag=False, default=False, help="Suppress logs and warnings."
+)
 @click.option(
     "-p",
     "--pages",

camelot/cli.py

@@ -25,7 +25,6 @@
 
 from .backends import ImageConversionBackend
 from .utils import build_file_path_in_temp_dir
-from .utils import compute_whitespace
 from .utils import get_index_closest_point
 from .utils import get_textline_coords
 
@@ -611,20 +610,6 @@ def parsing_report(self):
         }
         return report
 
-    def record_metadata(self, parser):
-        """Record data about the origin of the table."""
-        self.flavor = parser.id
-        self.filename = parser.filename
-        self.debug_info = parser.debug_info
-        if parser.copy_text is not None:
-            self.copy_spanning_text(parser.copy_text)
-        data = self.data
-        self.df = pd.DataFrame(data)
-        self.shape = self.df.shape
-
-        self.whitespace = compute_whitespace(data)
-        self.pdf_size = (parser.pdf_width, parser.pdf_height)
-
     def get_pdf_image(self):
         """Compute pdf image and cache it."""
         if self._image is None: