Merge branch 'master' into format-markdown
Vinayak Mehta
GitHub
commit
acb8f005c2
|
|
@ -10,20 +10,25 @@ assignees: ''
|
||||||
<!-- Please read the filing issues section of the contributor's guide first: https://camelot-py.readthedocs.io/en/master/dev/contributing.html -->
|
<!-- Please read the filing issues section of the contributor's guide first: https://camelot-py.readthedocs.io/en/master/dev/contributing.html -->
|
||||||
|
|
||||||
**Describe the bug**
|
**Describe the bug**
|
||||||
A clear and concise description of what the bug is.
|
|
||||||
|
<!-- A clear and concise description of what the bug is. -->
|
||||||
|
|
||||||
**Steps to reproduce the bug**
|
**Steps to reproduce the bug**
|
||||||
Steps used to install `camelot`:
|
|
||||||
1. Add step here (you can add more steps too)
|
|
||||||
|
|
||||||
Steps to reproduce the behavior:
|
<!-- Steps used to install `camelot`:
|
||||||
1. Add step here (you can add more steps too)
|
1. Add step here (you can add more steps too) -->
|
||||||
|
|
||||||
|
<!-- Steps to be used to reproduce behavior:
|
||||||
|
1. Add step here (you can add more steps too) -->
|
||||||
|
|
||||||
**Expected behavior**
|
**Expected behavior**
|
||||||
A clear and concise description of what you expected to happen.
|
|
||||||
|
<!-- A clear and concise description of what you expected to happen. -->
|
||||||
|
|
||||||
**Code**
|
**Code**
|
||||||
Add the Camelot code snippet that you used.
|
|
||||||
|
<!-- Add the Camelot code snippet that you used. -->
|
||||||
|
|
||||||
```
|
```
|
||||||
import camelot
|
import camelot
|
||||||
|
|
||||||
|
|
@ -31,18 +36,22 @@ import camelot
|
||||||
```
|
```
|
||||||
|
|
||||||
**PDF**
|
**PDF**
|
||||||
Add the PDF file that you want to extract tables from.
|
|
||||||
|
<!-- Add the PDF file that you want to extract tables from. -->
|
||||||
|
|
||||||
**Screenshots**
|
**Screenshots**
|
||||||
If applicable, add screenshots to help explain your problem.
|
|
||||||
|
<!-- If applicable, add screenshots to help explain your problem. -->
|
||||||
|
|
||||||
**Environment**
|
**Environment**
|
||||||
- OS: [e.g. MacOS]
|
|
||||||
- Python version:
|
- OS: [e.g. macOS]
|
||||||
- Numpy version:
|
- Python version:
|
||||||
- OpenCV version:
|
- Numpy version:
|
||||||
- Ghostscript version:
|
- OpenCV version:
|
||||||
- Camelot version:
|
- Ghostscript version:
|
||||||
|
- Camelot version:
|
||||||
|
|
||||||
**Additional context**
|
**Additional context**
|
||||||
Add any other context about the problem here.
|
|
||||||
|
<!-- Add any other context about the problem here. -->
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,23 @@
|
||||||
|
name: tests
|
||||||
|
|
||||||
|
on: [pull_request]
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
test:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
strategy:
|
||||||
|
matrix:
|
||||||
|
python-version: [3.6, 3.7, 3.8, 3.9]
|
||||||
|
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v2
|
||||||
|
- name: Set up Python ${{ matrix.python-version }}
|
||||||
|
uses: actions/setup-python@v2
|
||||||
|
with:
|
||||||
|
python-version: ${{ matrix.python-version }}
|
||||||
|
- name: Install camelot with dependencies
|
||||||
|
run: |
|
||||||
|
make install
|
||||||
|
- name: Test with pytest
|
||||||
|
run: |
|
||||||
|
make test
|
||||||
29
.travis.yml
29
.travis.yml
|
|
@ -1,29 +0,0 @@
|
||||||
sudo: true
|
|
||||||
language: python
|
|
||||||
cache: pip
|
|
||||||
addons:
|
|
||||||
apt:
|
|
||||||
update: true
|
|
||||||
install:
|
|
||||||
- make install
|
|
||||||
jobs:
|
|
||||||
include:
|
|
||||||
- stage: test
|
|
||||||
script:
|
|
||||||
- make test
|
|
||||||
python: '3.6'
|
|
||||||
- stage: test
|
|
||||||
script:
|
|
||||||
- make test
|
|
||||||
python: '3.7'
|
|
||||||
dist: xenial
|
|
||||||
- stage: test
|
|
||||||
script:
|
|
||||||
- make test
|
|
||||||
python: '3.8'
|
|
||||||
dist: xenial
|
|
||||||
- stage: coverage
|
|
||||||
python: '3.8'
|
|
||||||
script:
|
|
||||||
- make test
|
|
||||||
- codecov --verbose
|
|
||||||
27
HISTORY.md
27
HISTORY.md
|
|
@ -4,6 +4,33 @@ Release History
|
||||||
master
|
master
|
||||||
------
|
------
|
||||||
|
|
||||||
|
- Add faq section. [#216](https://github.com/camelot-dev/camelot/pull/216) by [Stefano Fiorucci](https://github.com/anakin87).
|
||||||
|
|
||||||
|
0.9.0 (2021-06-15)
|
||||||
|
------------------
|
||||||
|
|
||||||
|
**Bugfixes**
|
||||||
|
|
||||||
|
- Fix use of resolution argument to generate image with ghostscript. [#231](https://github.com/camelot-dev/camelot/pull/231) by [Tiago Samaha Cordeiro](https://github.com/tiagosamaha).
|
||||||
|
- [#15](https://github.com/camelot-dev/camelot/issues/15) Fix duplicate strings being assigned to the same cell. [#206](https://github.com/camelot-dev/camelot/pull/206) by [Eduardo Gonzalez Lopez de Murillas](https://github.com/edugonza).
|
||||||
|
- Save plot when filename is specified. [#121](https://github.com/camelot-dev/camelot/pull/121) by [Jens Diemer](https://github.com/jedie).
|
||||||
|
- Close file streams explicitly. [#202](https://github.com/camelot-dev/camelot/pull/202) by [Martin Abente Lahaye](https://github.com/tchx84).
|
||||||
|
- Use correct re.sub signature. [#186](https://github.com/camelot-dev/camelot/pull/186) by [pevisscher](https://github.com/pevisscher).
|
||||||
|
- [#183](https://github.com/camelot-dev/camelot/issues/183) Fix UnicodeEncodeError when using Stream flavor by adding encoding kwarg to `to_html`. [#188](https://github.com/camelot-dev/camelot/pull/188) by [Stefano Fiorucci](https://github.com/anakin87).
|
||||||
|
- [#179](https://github.com/camelot-dev/camelot/issues/179) Fix `max() arg is an empty sequence` error on PDFs with blank pages. [#189](https://github.com/camelot-dev/camelot/pull/189) by Vinayak Mehta.
|
||||||
|
|
||||||
|
**Improvements**
|
||||||
|
|
||||||
|
- Add `line_overlap` and `boxes_flow` to `LAParams`. [#219](https://github.com/camelot-dev/camelot/pull/219) by [Arnie97](https://github.com/Arnie97).
|
||||||
|
- [Add bug report template.](https://github.com/camelot-dev/camelot/commit/0a3944e54d133b701edfe9c7546ff11289301ba8)
|
||||||
|
- Move from [Travis to GitHub Actions](https://github.com/camelot-dev/camelot/pull/241).
|
||||||
|
- Update `.readthedocs.yml` and [remove requirements.txt](https://github.com/camelot-dev/camelot/commit/7ab5db39d07baa4063f975e9e00f6073340e04c1#diff-cde814ef2f549dc093f5b8fc533b7e8f47e7b32a8081e0760e57d5c25a1139d9)
|
||||||
|
|
||||||
|
**Documentation**
|
||||||
|
|
||||||
|
- [#193](https://github.com/camelot-dev/camelot/issues/193) Add better checks to confirm proper installation of ghostscript. [#196](https://github.com/camelot-dev/camelot/pull/196) by [jimhall](https://github.com/jimhall).
|
||||||
|
- Update `advanced.rst` plotting examples. [#119](https://github.com/camelot-dev/camelot/pull/119) by [Jens Diemer](https://github.com/jedie).
|
||||||
|
|
||||||
0.8.2 (2020-07-27)
|
0.8.2 (2020-07-27)
|
||||||
------------------
|
------------------
|
||||||
|
|
||||||
|
|
|
||||||
2
LICENSE
2
LICENSE
|
|
@ -1,6 +1,6 @@
|
||||||
MIT License
|
MIT License
|
||||||
|
|
||||||
Copyright (c) 2019-2020 Camelot Developers
|
Copyright (c) 2019-2021 Camelot Developers
|
||||||
Copyright (c) 2018-2019 Peeply Private Ltd (Singapore)
|
Copyright (c) 2018-2019 Peeply Private Ltd (Singapore)
|
||||||
|
|
||||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||||
|
|
|
||||||
11
README.md
11
README.md
|
|
@ -4,11 +4,10 @@
|
||||||
|
|
||||||
# Camelot: PDF Table Extraction for Humans
|
# Camelot: PDF Table Extraction for Humans
|
||||||
|
|
||||||
[](https://travis-ci.org/camelot-dev/camelot) [](https://camelot-py.readthedocs.io/en/master/)
|
 [](https://camelot-py.readthedocs.io/en/master/)
|
||||||
[](https://codecov.io/github/camelot-dev/camelot?branch=master)
|
[](https://codecov.io/github/camelot-dev/camelot?branch=master)
|
||||||
[](https://pypi.org/project/camelot-py/) [](https://pypi.org/project/camelot-py/) [](https://pypi.org/project/camelot-py/) [](https://gitter.im/camelot-dev/Lobby)
|
[](https://pypi.org/project/camelot-py/) [](https://pypi.org/project/camelot-py/) [](https://pypi.org/project/camelot-py/) [](https://gitter.im/camelot-dev/Lobby)
|
||||||
[](https://github.com/ambv/black) [](https://deepsource.io/gh/camelot-dev/camelot/?ref=repository-badge)
|
[](https://github.com/ambv/black)
|
||||||
|
|
||||||
|
|
||||||
**Camelot** is a Python library that can help you extract tables from PDFs!
|
**Camelot** is a Python library that can help you extract tables from PDFs!
|
||||||
|
|
||||||
|
|
@ -50,10 +49,12 @@ Camelot also comes packaged with a [command-line interface](https://camelot-py.r
|
||||||
|
|
||||||
**Note:** Camelot 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".)
|
**Note:** Camelot 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://camelot-py.readthedocs.io/en/master/user/faq.html).
|
||||||
|
|
||||||
## Why Camelot?
|
## Why Camelot?
|
||||||
|
|
||||||
- **Configurability**: Camelot gives you control over the table extraction process with its [tweakable settings](https://camelot-py.readthedocs.io/en/master/user/advanced.html).
|
- **Configurability**: Camelot gives you control over the table extraction process with [tweakable settings](https://camelot-py.readthedocs.io/en/master/user/advanced.html).
|
||||||
- **Metrics**: Bad tables can be discarded based on metrics like accuracy and whitespace, without having to manually look at each table.
|
- **Metrics**: You can discard bad tables based on metrics like accuracy and whitespace, without having to manually look at each table.
|
||||||
- **Output**: Each table is extracted into a **pandas DataFrame**, which seamlessly integrates into [ETL and data analysis workflows](https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873). You can also export tables to multiple formats, which include CSV, JSON, Excel, HTML and Sqlite.
|
- **Output**: Each table is extracted into a **pandas DataFrame**, which seamlessly integrates into [ETL and data analysis workflows](https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873). You can also export tables to multiple formats, which include CSV, JSON, Excel, HTML and Sqlite.
|
||||||
|
|
||||||
See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
|
See [comparison with similar libraries and tools](https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools).
|
||||||
|
|
|
||||||
|
|
@ -1,6 +1,6 @@
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
VERSION = (0, 8, 2)
|
VERSION = (0, 9, 0)
|
||||||
PRERELEASE = None # alpha, beta or rc
|
PRERELEASE = None # alpha, beta or rc
|
||||||
REVISION = None
|
REVISION = None
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -55,7 +55,9 @@ class TextEdge(object):
|
||||||
x = round(self.x, 2)
|
x = round(self.x, 2)
|
||||||
y0 = round(self.y0, 2)
|
y0 = round(self.y0, 2)
|
||||||
y1 = round(self.y1, 2)
|
y1 = round(self.y1, 2)
|
||||||
return f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
|
return (
|
||||||
|
f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
|
||||||
|
)
|
||||||
|
|
||||||
def update_coords(self, x, y0, edge_tol=50):
|
def update_coords(self, x, y0, edge_tol=50):
|
||||||
"""Updates the text edge's x and bottom y coordinates and sets
|
"""Updates the text edge's x and bottom y coordinates and sets
|
||||||
|
|
@ -102,8 +104,7 @@ class TextEdges(object):
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def add(self, textline, align):
|
def add(self, textline, align):
|
||||||
"""Adds a new text edge to the current dict.
|
"""Adds a new text edge to the current dict."""
|
||||||
"""
|
|
||||||
x = self.get_x_coord(textline, align)
|
x = self.get_x_coord(textline, align)
|
||||||
y0 = textline.y0
|
y0 = textline.y0
|
||||||
y1 = textline.y1
|
y1 = textline.y1
|
||||||
|
|
@ -111,8 +112,7 @@ class TextEdges(object):
|
||||||
self._textedges[align].append(te)
|
self._textedges[align].append(te)
|
||||||
|
|
||||||
def update(self, textline):
|
def update(self, textline):
|
||||||
"""Updates an existing text edge in the current dict.
|
"""Updates an existing text edge in the current dict."""
|
||||||
"""
|
|
||||||
for align in ["left", "right", "middle"]:
|
for align in ["left", "right", "middle"]:
|
||||||
x_coord = self.get_x_coord(textline, align)
|
x_coord = self.get_x_coord(textline, align)
|
||||||
idx = self.find(x_coord, align)
|
idx = self.find(x_coord, align)
|
||||||
|
|
@ -304,8 +304,7 @@ class Cell(object):
|
||||||
|
|
||||||
@property
|
@property
|
||||||
def bound(self):
|
def bound(self):
|
||||||
"""The number of sides on which the cell is bounded.
|
"""The number of sides on which the cell is bounded."""
|
||||||
"""
|
|
||||||
return self.top + self.bottom + self.left + self.right
|
return self.top + self.bottom + self.left + self.right
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -361,8 +360,7 @@ class Table(object):
|
||||||
|
|
||||||
@property
|
@property
|
||||||
def data(self):
|
def data(self):
|
||||||
"""Returns two-dimensional list of strings in table.
|
"""Returns two-dimensional list of strings in table."""
|
||||||
"""
|
|
||||||
d = []
|
d = []
|
||||||
for row in self.cells:
|
for row in self.cells:
|
||||||
d.append([cell.text.strip() for cell in row])
|
d.append([cell.text.strip() for cell in row])
|
||||||
|
|
@ -383,8 +381,7 @@ class Table(object):
|
||||||
return report
|
return report
|
||||||
|
|
||||||
def set_all_edges(self):
|
def set_all_edges(self):
|
||||||
"""Sets all table edges to True.
|
"""Sets all table edges to True."""
|
||||||
"""
|
|
||||||
for row in self.cells:
|
for row in self.cells:
|
||||||
for cell in row:
|
for cell in row:
|
||||||
cell.left = cell.right = cell.top = cell.bottom = True
|
cell.left = cell.right = cell.top = cell.bottom = True
|
||||||
|
|
@ -526,8 +523,7 @@ class Table(object):
|
||||||
return self
|
return self
|
||||||
|
|
||||||
def set_border(self):
|
def set_border(self):
|
||||||
"""Sets table border edges to True.
|
"""Sets table border edges to True."""
|
||||||
"""
|
|
||||||
for r in range(len(self.rows)):
|
for r in range(len(self.rows)):
|
||||||
self.cells[r][0].left = True
|
self.cells[r][0].left = True
|
||||||
self.cells[r][len(self.cols) - 1].right = True
|
self.cells[r][len(self.cols) - 1].right = True
|
||||||
|
|
|
||||||
|
|
@ -81,8 +81,7 @@ class __Ghostscript(object):
|
||||||
|
|
||||||
|
|
||||||
def Ghostscript(*args, **kwargs):
|
def Ghostscript(*args, **kwargs):
|
||||||
"""Factory function for setting up a Ghostscript instance
|
"""Factory function for setting up a Ghostscript instance"""
|
||||||
"""
|
|
||||||
global __instance__
|
global __instance__
|
||||||
# Ghostscript only supports a single instance
|
# Ghostscript only supports a single instance
|
||||||
if __instance__ is None:
|
if __instance__ is None:
|
||||||
|
|
|
||||||
|
|
@ -167,9 +167,7 @@ class PDFHandler(object):
|
||||||
with TemporaryDirectory() as tempdir:
|
with TemporaryDirectory() as tempdir:
|
||||||
for p in self.pages:
|
for p in self.pages:
|
||||||
self._save_page(self.filepath, p, tempdir)
|
self._save_page(self.filepath, p, tempdir)
|
||||||
pages = [
|
pages = [os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages]
|
||||||
os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages
|
|
||||||
]
|
|
||||||
parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
|
parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
|
||||||
for p in pages:
|
for p in pages:
|
||||||
t = parser.extract_tables(
|
t = parser.extract_tables(
|
||||||
|
|
|
||||||
|
|
@ -6,8 +6,7 @@ from ..utils import get_page_layout, get_text_objects
|
||||||
|
|
||||||
|
|
||||||
class BaseParser(object):
|
class BaseParser(object):
|
||||||
"""Defines a base parser.
|
"""Defines a base parser."""
|
||||||
"""
|
|
||||||
|
|
||||||
def _generate_layout(self, filename, layout_kwargs):
|
def _generate_layout(self, filename, layout_kwargs):
|
||||||
self.filename = filename
|
self.filename = filename
|
||||||
|
|
|
||||||
|
|
@ -211,8 +211,8 @@ class Lattice(BaseParser):
|
||||||
from ..ext.ghostscript import Ghostscript
|
from ..ext.ghostscript import Ghostscript
|
||||||
|
|
||||||
self.imagename = "".join([self.rootname, ".png"])
|
self.imagename = "".join([self.rootname, ".png"])
|
||||||
gs_call = "-q -sDEVICE=png16m -o {} -r300 {}".format(
|
gs_call = "-q -sDEVICE=png16m -o {} -r{} {}".format(
|
||||||
self.imagename, self.filename
|
self.imagename, self.resolution, self.filename
|
||||||
)
|
)
|
||||||
gs_call = gs_call.encode().split()
|
gs_call = gs_call.encode().split()
|
||||||
null = open(os.devnull, "wb")
|
null = open(os.devnull, "wb")
|
||||||
|
|
|
||||||
|
|
@ -65,7 +65,7 @@ class Stream(BaseParser):
|
||||||
edge_tol=50,
|
edge_tol=50,
|
||||||
row_tol=2,
|
row_tol=2,
|
||||||
column_tol=0,
|
column_tol=0,
|
||||||
**kwargs
|
**kwargs,
|
||||||
):
|
):
|
||||||
self.table_regions = table_regions
|
self.table_regions = table_regions
|
||||||
self.table_areas = table_areas
|
self.table_areas = table_areas
|
||||||
|
|
@ -362,10 +362,10 @@ class Stream(BaseParser):
|
||||||
if len(elements):
|
if len(elements):
|
||||||
ncols = max(set(elements), key=elements.count)
|
ncols = max(set(elements), key=elements.count)
|
||||||
else:
|
else:
|
||||||
warnings.warn(
|
warnings.warn(f"No tables found in table area {table_idx + 1}")
|
||||||
f"No tables found in table area {table_idx + 1}"
|
cols = [
|
||||||
)
|
(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r
|
||||||
cols = [(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r]
|
]
|
||||||
cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
|
cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
|
||||||
inner_text = []
|
inner_text = []
|
||||||
for i in range(1, len(cols)):
|
for i in range(1, len(cols)):
|
||||||
|
|
|
||||||
|
|
@ -34,13 +34,9 @@ class PlotMethods(object):
|
||||||
raise ImportError("matplotlib is required for plotting.")
|
raise ImportError("matplotlib is required for plotting.")
|
||||||
|
|
||||||
if table.flavor == "lattice" and kind in ["textedge"]:
|
if table.flavor == "lattice" and kind in ["textedge"]:
|
||||||
raise NotImplementedError(
|
raise NotImplementedError(f"Lattice flavor does not support kind='{kind}'")
|
||||||
f"Lattice flavor does not support kind='{kind}'"
|
|
||||||
)
|
|
||||||
elif table.flavor == "stream" and kind in ["joint", "line"]:
|
elif table.flavor == "stream" and kind in ["joint", "line"]:
|
||||||
raise NotImplementedError(
|
raise NotImplementedError(f"Stream flavor does not support kind='{kind}'")
|
||||||
f"Stream flavor does not support kind='{kind}'"
|
|
||||||
)
|
|
||||||
|
|
||||||
plot_method = getattr(self, kind)
|
plot_method = getattr(self, kind)
|
||||||
fig = plot_method(table)
|
fig = plot_method(table)
|
||||||
|
|
@ -48,7 +44,7 @@ class PlotMethods(object):
|
||||||
if filename is not None:
|
if filename is not None:
|
||||||
fig.savefig(filename)
|
fig.savefig(filename)
|
||||||
return None
|
return None
|
||||||
|
|
||||||
return fig
|
return fig
|
||||||
|
|
||||||
def text(self, table):
|
def text(self, table):
|
||||||
|
|
|
||||||
|
|
@ -838,23 +838,27 @@ def compute_whitespace(d):
|
||||||
|
|
||||||
def get_page_layout(
|
def get_page_layout(
|
||||||
filename,
|
filename,
|
||||||
|
line_overlap=0.5,
|
||||||
char_margin=1.0,
|
char_margin=1.0,
|
||||||
line_margin=0.5,
|
line_margin=0.5,
|
||||||
word_margin=0.1,
|
word_margin=0.1,
|
||||||
|
boxes_flow=0.5,
|
||||||
detect_vertical=True,
|
detect_vertical=True,
|
||||||
all_texts=True,
|
all_texts=True,
|
||||||
):
|
):
|
||||||
"""Returns a PDFMiner LTPage object and page dimension of a single
|
"""Returns a PDFMiner LTPage object and page dimension of a single
|
||||||
page pdf. See https://euske.github.io/pdfminer/ to get definitions
|
page pdf. To get the definitions of kwargs, see
|
||||||
of kwargs.
|
https://pdfminersix.rtfd.io/en/latest/reference/composable.html.
|
||||||
|
|
||||||
Parameters
|
Parameters
|
||||||
----------
|
----------
|
||||||
filename : string
|
filename : string
|
||||||
Path to pdf file.
|
Path to pdf file.
|
||||||
|
line_overlap : float
|
||||||
char_margin : float
|
char_margin : float
|
||||||
line_margin : float
|
line_margin : float
|
||||||
word_margin : float
|
word_margin : float
|
||||||
|
boxes_flow : float
|
||||||
detect_vertical : bool
|
detect_vertical : bool
|
||||||
all_texts : bool
|
all_texts : bool
|
||||||
|
|
||||||
|
|
@ -870,11 +874,15 @@ def get_page_layout(
|
||||||
parser = PDFParser(f)
|
parser = PDFParser(f)
|
||||||
document = PDFDocument(parser)
|
document = PDFDocument(parser)
|
||||||
if not document.is_extractable:
|
if not document.is_extractable:
|
||||||
raise PDFTextExtractionNotAllowed(f"Text extraction is not allowed: {filename}")
|
raise PDFTextExtractionNotAllowed(
|
||||||
|
f"Text extraction is not allowed: {filename}"
|
||||||
|
)
|
||||||
laparams = LAParams(
|
laparams = LAParams(
|
||||||
|
line_overlap=line_overlap,
|
||||||
char_margin=char_margin,
|
char_margin=char_margin,
|
||||||
line_margin=line_margin,
|
line_margin=line_margin,
|
||||||
word_margin=word_margin,
|
word_margin=word_margin,
|
||||||
|
boxes_flow=boxes_flow,
|
||||||
detect_vertical=detect_vertical,
|
detect_vertical=detect_vertical,
|
||||||
all_texts=all_texts,
|
all_texts=all_texts,
|
||||||
)
|
)
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,19 @@
|
||||||
# flasky pygments style based on tango style
|
# flasky pygments style based on tango style
|
||||||
from pygments.style import Style
|
from pygments.style import Style
|
||||||
from pygments.token import Keyword, Name, Comment, String, Error, \
|
from pygments.token import (
|
||||||
Number, Operator, Generic, Whitespace, Punctuation, Other, Literal
|
Keyword,
|
||||||
|
Name,
|
||||||
|
Comment,
|
||||||
|
String,
|
||||||
|
Error,
|
||||||
|
Number,
|
||||||
|
Operator,
|
||||||
|
Generic,
|
||||||
|
Whitespace,
|
||||||
|
Punctuation,
|
||||||
|
Other,
|
||||||
|
Literal,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class FlaskyStyle(Style):
|
class FlaskyStyle(Style):
|
||||||
|
|
@ -11,76 +23,67 @@ class FlaskyStyle(Style):
|
||||||
styles = {
|
styles = {
|
||||||
# No corresponding class for the following:
|
# No corresponding class for the following:
|
||||||
# Text: "", # class: ''
|
# Text: "", # class: ''
|
||||||
Whitespace: "underline #f8f8f8", # class: 'w'
|
Whitespace: "underline #f8f8f8", # class: 'w'
|
||||||
Error: "#a40000 border:#ef2929", # class: 'err'
|
Error: "#a40000 border:#ef2929", # class: 'err'
|
||||||
Other: "#000000", # class 'x'
|
Other: "#000000", # class 'x'
|
||||||
|
Comment: "italic #8f5902", # class: 'c'
|
||||||
Comment: "italic #8f5902", # class: 'c'
|
Comment.Preproc: "noitalic", # class: 'cp'
|
||||||
Comment.Preproc: "noitalic", # class: 'cp'
|
Keyword: "bold #004461", # class: 'k'
|
||||||
|
Keyword.Constant: "bold #004461", # class: 'kc'
|
||||||
Keyword: "bold #004461", # class: 'k'
|
Keyword.Declaration: "bold #004461", # class: 'kd'
|
||||||
Keyword.Constant: "bold #004461", # class: 'kc'
|
Keyword.Namespace: "bold #004461", # class: 'kn'
|
||||||
Keyword.Declaration: "bold #004461", # class: 'kd'
|
Keyword.Pseudo: "bold #004461", # class: 'kp'
|
||||||
Keyword.Namespace: "bold #004461", # class: 'kn'
|
Keyword.Reserved: "bold #004461", # class: 'kr'
|
||||||
Keyword.Pseudo: "bold #004461", # class: 'kp'
|
Keyword.Type: "bold #004461", # class: 'kt'
|
||||||
Keyword.Reserved: "bold #004461", # class: 'kr'
|
Operator: "#582800", # class: 'o'
|
||||||
Keyword.Type: "bold #004461", # class: 'kt'
|
Operator.Word: "bold #004461", # class: 'ow' - like keywords
|
||||||
|
Punctuation: "bold #000000", # class: 'p'
|
||||||
Operator: "#582800", # class: 'o'
|
|
||||||
Operator.Word: "bold #004461", # class: 'ow' - like keywords
|
|
||||||
|
|
||||||
Punctuation: "bold #000000", # class: 'p'
|
|
||||||
|
|
||||||
# because special names such as Name.Class, Name.Function, etc.
|
# because special names such as Name.Class, Name.Function, etc.
|
||||||
# are not recognized as such later in the parsing, we choose them
|
# are not recognized as such later in the parsing, we choose them
|
||||||
# to look the same as ordinary variables.
|
# to look the same as ordinary variables.
|
||||||
Name: "#000000", # class: 'n'
|
Name: "#000000", # class: 'n'
|
||||||
Name.Attribute: "#c4a000", # class: 'na' - to be revised
|
Name.Attribute: "#c4a000", # class: 'na' - to be revised
|
||||||
Name.Builtin: "#004461", # class: 'nb'
|
Name.Builtin: "#004461", # class: 'nb'
|
||||||
Name.Builtin.Pseudo: "#3465a4", # class: 'bp'
|
Name.Builtin.Pseudo: "#3465a4", # class: 'bp'
|
||||||
Name.Class: "#000000", # class: 'nc' - to be revised
|
Name.Class: "#000000", # class: 'nc' - to be revised
|
||||||
Name.Constant: "#000000", # class: 'no' - to be revised
|
Name.Constant: "#000000", # class: 'no' - to be revised
|
||||||
Name.Decorator: "#888", # class: 'nd' - to be revised
|
Name.Decorator: "#888", # class: 'nd' - to be revised
|
||||||
Name.Entity: "#ce5c00", # class: 'ni'
|
Name.Entity: "#ce5c00", # class: 'ni'
|
||||||
Name.Exception: "bold #cc0000", # class: 'ne'
|
Name.Exception: "bold #cc0000", # class: 'ne'
|
||||||
Name.Function: "#000000", # class: 'nf'
|
Name.Function: "#000000", # class: 'nf'
|
||||||
Name.Property: "#000000", # class: 'py'
|
Name.Property: "#000000", # class: 'py'
|
||||||
Name.Label: "#f57900", # class: 'nl'
|
Name.Label: "#f57900", # class: 'nl'
|
||||||
Name.Namespace: "#000000", # class: 'nn' - to be revised
|
Name.Namespace: "#000000", # class: 'nn' - to be revised
|
||||||
Name.Other: "#000000", # class: 'nx'
|
Name.Other: "#000000", # class: 'nx'
|
||||||
Name.Tag: "bold #004461", # class: 'nt' - like a keyword
|
Name.Tag: "bold #004461", # class: 'nt' - like a keyword
|
||||||
Name.Variable: "#000000", # class: 'nv' - to be revised
|
Name.Variable: "#000000", # class: 'nv' - to be revised
|
||||||
Name.Variable.Class: "#000000", # class: 'vc' - to be revised
|
Name.Variable.Class: "#000000", # class: 'vc' - to be revised
|
||||||
Name.Variable.Global: "#000000", # class: 'vg' - to be revised
|
Name.Variable.Global: "#000000", # class: 'vg' - to be revised
|
||||||
Name.Variable.Instance: "#000000", # class: 'vi' - to be revised
|
Name.Variable.Instance: "#000000", # class: 'vi' - to be revised
|
||||||
|
Number: "#990000", # class: 'm'
|
||||||
Number: "#990000", # class: 'm'
|
Literal: "#000000", # class: 'l'
|
||||||
|
Literal.Date: "#000000", # class: 'ld'
|
||||||
Literal: "#000000", # class: 'l'
|
String: "#4e9a06", # class: 's'
|
||||||
Literal.Date: "#000000", # class: 'ld'
|
String.Backtick: "#4e9a06", # class: 'sb'
|
||||||
|
String.Char: "#4e9a06", # class: 'sc'
|
||||||
String: "#4e9a06", # class: 's'
|
String.Doc: "italic #8f5902", # class: 'sd' - like a comment
|
||||||
String.Backtick: "#4e9a06", # class: 'sb'
|
String.Double: "#4e9a06", # class: 's2'
|
||||||
String.Char: "#4e9a06", # class: 'sc'
|
String.Escape: "#4e9a06", # class: 'se'
|
||||||
String.Doc: "italic #8f5902", # class: 'sd' - like a comment
|
String.Heredoc: "#4e9a06", # class: 'sh'
|
||||||
String.Double: "#4e9a06", # class: 's2'
|
String.Interpol: "#4e9a06", # class: 'si'
|
||||||
String.Escape: "#4e9a06", # class: 'se'
|
String.Other: "#4e9a06", # class: 'sx'
|
||||||
String.Heredoc: "#4e9a06", # class: 'sh'
|
String.Regex: "#4e9a06", # class: 'sr'
|
||||||
String.Interpol: "#4e9a06", # class: 'si'
|
String.Single: "#4e9a06", # class: 's1'
|
||||||
String.Other: "#4e9a06", # class: 'sx'
|
String.Symbol: "#4e9a06", # class: 'ss'
|
||||||
String.Regex: "#4e9a06", # class: 'sr'
|
Generic: "#000000", # class: 'g'
|
||||||
String.Single: "#4e9a06", # class: 's1'
|
Generic.Deleted: "#a40000", # class: 'gd'
|
||||||
String.Symbol: "#4e9a06", # class: 'ss'
|
Generic.Emph: "italic #000000", # class: 'ge'
|
||||||
|
Generic.Error: "#ef2929", # class: 'gr'
|
||||||
Generic: "#000000", # class: 'g'
|
Generic.Heading: "bold #000080", # class: 'gh'
|
||||||
Generic.Deleted: "#a40000", # class: 'gd'
|
Generic.Inserted: "#00A000", # class: 'gi'
|
||||||
Generic.Emph: "italic #000000", # class: 'ge'
|
Generic.Output: "#888", # class: 'go'
|
||||||
Generic.Error: "#ef2929", # class: 'gr'
|
Generic.Prompt: "#745334", # class: 'gp'
|
||||||
Generic.Heading: "bold #000080", # class: 'gh'
|
Generic.Strong: "bold #000000", # class: 'gs'
|
||||||
Generic.Inserted: "#00A000", # class: 'gi'
|
Generic.Subheading: "bold #800080", # class: 'gu'
|
||||||
Generic.Output: "#888", # class: 'go'
|
Generic.Traceback: "bold #a40000", # class: 'gt'
|
||||||
Generic.Prompt: "#745334", # class: 'gp'
|
|
||||||
Generic.Strong: "bold #000000", # class: 'gs'
|
|
||||||
Generic.Subheading: "bold #800080", # class: 'gu'
|
|
||||||
Generic.Traceback: "bold #a40000", # class: 'gt'
|
|
||||||
}
|
}
|
||||||
|
|
|
||||||
120
docs/conf.py
120
docs/conf.py
|
|
@ -22,8 +22,8 @@ import sys
|
||||||
# sys.path.insert(0, os.path.abspath('..'))
|
# sys.path.insert(0, os.path.abspath('..'))
|
||||||
|
|
||||||
# Insert Camelot's path into the system.
|
# Insert Camelot's path into the system.
|
||||||
sys.path.insert(0, os.path.abspath('..'))
|
sys.path.insert(0, os.path.abspath(".."))
|
||||||
sys.path.insert(0, os.path.abspath('_themes'))
|
sys.path.insert(0, os.path.abspath("_themes"))
|
||||||
|
|
||||||
import camelot
|
import camelot
|
||||||
|
|
||||||
|
|
@ -38,33 +38,33 @@ import camelot
|
||||||
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
|
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
|
||||||
# ones.
|
# ones.
|
||||||
extensions = [
|
extensions = [
|
||||||
'sphinx.ext.autodoc',
|
"sphinx.ext.autodoc",
|
||||||
'sphinx.ext.napoleon',
|
"sphinx.ext.napoleon",
|
||||||
'sphinx.ext.intersphinx',
|
"sphinx.ext.intersphinx",
|
||||||
'sphinx.ext.todo',
|
"sphinx.ext.todo",
|
||||||
'sphinx.ext.viewcode',
|
"sphinx.ext.viewcode",
|
||||||
]
|
]
|
||||||
|
|
||||||
# Add any paths that contain templates here, relative to this directory.
|
# Add any paths that contain templates here, relative to this directory.
|
||||||
templates_path = ['_templates']
|
templates_path = ["_templates"]
|
||||||
|
|
||||||
# The suffix(es) of source filenames.
|
# The suffix(es) of source filenames.
|
||||||
# You can specify multiple suffix as a list of string:
|
# You can specify multiple suffix as a list of string:
|
||||||
#
|
#
|
||||||
# source_suffix = ['.rst', '.md']
|
# source_suffix = ['.rst', '.md']
|
||||||
source_suffix = '.rst'
|
source_suffix = ".rst"
|
||||||
|
|
||||||
# The encoding of source files.
|
# The encoding of source files.
|
||||||
#
|
#
|
||||||
# source_encoding = 'utf-8-sig'
|
# source_encoding = 'utf-8-sig'
|
||||||
|
|
||||||
# The master toctree document.
|
# The master toctree document.
|
||||||
master_doc = 'index'
|
master_doc = "index"
|
||||||
|
|
||||||
# General information about the project.
|
# General information about the project.
|
||||||
project = u'Camelot'
|
project = u"Camelot"
|
||||||
copyright = u'2020, Camelot Developers'
|
copyright = u"2021, Camelot Developers"
|
||||||
author = u'Vinayak Mehta'
|
author = u"Vinayak Mehta"
|
||||||
|
|
||||||
# The version info for the project you're documenting, acts as replacement for
|
# The version info for the project you're documenting, acts as replacement for
|
||||||
# |version| and |release|, also used in various other places throughout the
|
# |version| and |release|, also used in various other places throughout the
|
||||||
|
|
@ -94,7 +94,7 @@ language = None
|
||||||
# List of patterns, relative to source directory, that match files and
|
# List of patterns, relative to source directory, that match files and
|
||||||
# directories to ignore when looking for source files.
|
# directories to ignore when looking for source files.
|
||||||
# This patterns also effect to html_static_path and html_extra_path
|
# This patterns also effect to html_static_path and html_extra_path
|
||||||
exclude_patterns = ['_build']
|
exclude_patterns = ["_build"]
|
||||||
|
|
||||||
# The reST default role (used for this markup: `text`) to use for all
|
# The reST default role (used for this markup: `text`) to use for all
|
||||||
# documents.
|
# documents.
|
||||||
|
|
@ -114,7 +114,7 @@ add_module_names = True
|
||||||
# show_authors = False
|
# show_authors = False
|
||||||
|
|
||||||
# The name of the Pygments (syntax highlighting) style to use.
|
# The name of the Pygments (syntax highlighting) style to use.
|
||||||
pygments_style = 'flask_theme_support.FlaskyStyle'
|
pygments_style = "flask_theme_support.FlaskyStyle"
|
||||||
|
|
||||||
# A list of ignored prefixes for module index sorting.
|
# A list of ignored prefixes for module index sorting.
|
||||||
# modindex_common_prefix = []
|
# modindex_common_prefix = []
|
||||||
|
|
@ -130,18 +130,18 @@ todo_include_todos = True
|
||||||
|
|
||||||
# The theme to use for HTML and HTML Help pages. See the documentation for
|
# The theme to use for HTML and HTML Help pages. See the documentation for
|
||||||
# a list of builtin themes.
|
# a list of builtin themes.
|
||||||
html_theme = 'alabaster'
|
html_theme = "alabaster"
|
||||||
|
|
||||||
# Theme options are theme-specific and customize the look and feel of a theme
|
# Theme options are theme-specific and customize the look and feel of a theme
|
||||||
# further. For a list of options available for each theme, see the
|
# further. For a list of options available for each theme, see the
|
||||||
# documentation.
|
# documentation.
|
||||||
html_theme_options = {
|
html_theme_options = {
|
||||||
'show_powered_by': False,
|
"show_powered_by": False,
|
||||||
'github_user': 'camelot-dev',
|
"github_user": "camelot-dev",
|
||||||
'github_repo': 'camelot',
|
"github_repo": "camelot",
|
||||||
'github_banner': True,
|
"github_banner": True,
|
||||||
'show_related': False,
|
"show_related": False,
|
||||||
'note_bg': '#FFF59C'
|
"note_bg": "#FFF59C",
|
||||||
}
|
}
|
||||||
|
|
||||||
# Add any paths that contain custom themes here, relative to this directory.
|
# Add any paths that contain custom themes here, relative to this directory.
|
||||||
|
|
@ -164,12 +164,12 @@ html_theme_options = {
|
||||||
# The name of an image file (relative to this directory) to use as a favicon of
|
# The name of an image file (relative to this directory) to use as a favicon of
|
||||||
# the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
|
# the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
|
||||||
# pixels large.
|
# pixels large.
|
||||||
html_favicon = '_static/favicon.ico'
|
html_favicon = "_static/favicon.ico"
|
||||||
|
|
||||||
# Add any paths that contain custom static files (such as style sheets) here,
|
# Add any paths that contain custom static files (such as style sheets) here,
|
||||||
# relative to this directory. They are copied after the builtin static files,
|
# relative to this directory. They are copied after the builtin static files,
|
||||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||||
html_static_path = ['_static']
|
html_static_path = ["_static"]
|
||||||
|
|
||||||
# Add any extra paths that contain custom files (such as robots.txt or
|
# Add any extra paths that contain custom files (such as robots.txt or
|
||||||
# .htaccess) here, relative to this directory. These files are copied
|
# .htaccess) here, relative to this directory. These files are copied
|
||||||
|
|
@ -189,10 +189,21 @@ html_use_smartypants = True
|
||||||
|
|
||||||
# Custom sidebar templates, maps document names to template names.
|
# Custom sidebar templates, maps document names to template names.
|
||||||
html_sidebars = {
|
html_sidebars = {
|
||||||
'index': ['sidebarintro.html', 'relations.html', 'sourcelink.html',
|
"index": [
|
||||||
'searchbox.html', 'hacks.html'],
|
"sidebarintro.html",
|
||||||
'**': ['sidebarlogo.html', 'localtoc.html', 'relations.html',
|
"relations.html",
|
||||||
'sourcelink.html', 'searchbox.html', 'hacks.html']
|
"sourcelink.html",
|
||||||
|
"searchbox.html",
|
||||||
|
"hacks.html",
|
||||||
|
],
|
||||||
|
"**": [
|
||||||
|
"sidebarlogo.html",
|
||||||
|
"localtoc.html",
|
||||||
|
"relations.html",
|
||||||
|
"sourcelink.html",
|
||||||
|
"searchbox.html",
|
||||||
|
"hacks.html",
|
||||||
|
],
|
||||||
}
|
}
|
||||||
|
|
||||||
# Additional templates that should be rendered to pages, maps page names to
|
# Additional templates that should be rendered to pages, maps page names to
|
||||||
|
|
@ -249,34 +260,30 @@ html_show_copyright = True
|
||||||
# html_search_scorer = 'scorer.js'
|
# html_search_scorer = 'scorer.js'
|
||||||
|
|
||||||
# Output file base name for HTML help builder.
|
# Output file base name for HTML help builder.
|
||||||
htmlhelp_basename = 'Camelotdoc'
|
htmlhelp_basename = "Camelotdoc"
|
||||||
|
|
||||||
# -- Options for LaTeX output ---------------------------------------------
|
# -- Options for LaTeX output ---------------------------------------------
|
||||||
|
|
||||||
latex_elements = {
|
latex_elements = {
|
||||||
# The paper size ('letterpaper' or 'a4paper').
|
# The paper size ('letterpaper' or 'a4paper').
|
||||||
#
|
#
|
||||||
# 'papersize': 'letterpaper',
|
# 'papersize': 'letterpaper',
|
||||||
|
# The font size ('10pt', '11pt' or '12pt').
|
||||||
# The font size ('10pt', '11pt' or '12pt').
|
#
|
||||||
#
|
# 'pointsize': '10pt',
|
||||||
# 'pointsize': '10pt',
|
# Additional stuff for the LaTeX preamble.
|
||||||
|
#
|
||||||
# Additional stuff for the LaTeX preamble.
|
# 'preamble': '',
|
||||||
#
|
# Latex figure (float) alignment
|
||||||
# 'preamble': '',
|
#
|
||||||
|
# 'figure_align': 'htbp',
|
||||||
# Latex figure (float) alignment
|
|
||||||
#
|
|
||||||
# 'figure_align': 'htbp',
|
|
||||||
}
|
}
|
||||||
|
|
||||||
# Grouping the document tree into LaTeX files. List of tuples
|
# Grouping the document tree into LaTeX files. List of tuples
|
||||||
# (source start file, target name, title,
|
# (source start file, target name, title,
|
||||||
# author, documentclass [howto, manual, or own class]).
|
# author, documentclass [howto, manual, or own class]).
|
||||||
latex_documents = [
|
latex_documents = [
|
||||||
(master_doc, 'Camelot.tex', u'Camelot Documentation',
|
(master_doc, "Camelot.tex", u"Camelot Documentation", u"Vinayak Mehta", "manual"),
|
||||||
u'Vinayak Mehta', 'manual'),
|
|
||||||
]
|
]
|
||||||
|
|
||||||
# The name of an image file (relative to this directory) to place at the top of
|
# The name of an image file (relative to this directory) to place at the top of
|
||||||
|
|
@ -316,10 +323,7 @@ latex_documents = [
|
||||||
|
|
||||||
# One entry per manual page. List of tuples
|
# One entry per manual page. List of tuples
|
||||||
# (source start file, name, description, authors, manual section).
|
# (source start file, name, description, authors, manual section).
|
||||||
man_pages = [
|
man_pages = [(master_doc, "Camelot", u"Camelot Documentation", [author], 1)]
|
||||||
(master_doc, 'Camelot', u'Camelot Documentation',
|
|
||||||
[author], 1)
|
|
||||||
]
|
|
||||||
|
|
||||||
# If true, show URL addresses after external links.
|
# If true, show URL addresses after external links.
|
||||||
#
|
#
|
||||||
|
|
@ -332,9 +336,15 @@ man_pages = [
|
||||||
# (source start file, target name, title, author,
|
# (source start file, target name, title, author,
|
||||||
# dir menu entry, description, category)
|
# dir menu entry, description, category)
|
||||||
texinfo_documents = [
|
texinfo_documents = [
|
||||||
(master_doc, 'Camelot', u'Camelot Documentation',
|
(
|
||||||
author, 'Camelot', 'One line description of project.',
|
master_doc,
|
||||||
'Miscellaneous'),
|
"Camelot",
|
||||||
|
u"Camelot Documentation",
|
||||||
|
author,
|
||||||
|
"Camelot",
|
||||||
|
"One line description of project.",
|
||||||
|
"Miscellaneous",
|
||||||
|
),
|
||||||
]
|
]
|
||||||
|
|
||||||
# Documents to append as an appendix to all manuals.
|
# Documents to append as an appendix to all manuals.
|
||||||
|
|
@ -356,6 +366,6 @@ texinfo_documents = [
|
||||||
|
|
||||||
# Example configuration for intersphinx: refer to the Python standard library.
|
# Example configuration for intersphinx: refer to the Python standard library.
|
||||||
intersphinx_mapping = {
|
intersphinx_mapping = {
|
||||||
'https://docs.python.org/2': None,
|
"https://docs.python.org/2": None,
|
||||||
'http://pandas.pydata.org/pandas-docs/stable': None
|
"http://pandas.pydata.org/pandas-docs/stable": None,
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -110,6 +110,7 @@ This part of the documentation begins with some background information about why
|
||||||
user/how-it-works
|
user/how-it-works
|
||||||
user/quickstart
|
user/quickstart
|
||||||
user/advanced
|
user/advanced
|
||||||
|
user/faq
|
||||||
user/cli
|
user/cli
|
||||||
|
|
||||||
The API Documentation/Guide
|
The API Documentation/Guide
|
||||||
|
|
|
||||||
|
|
@ -618,7 +618,7 @@ Tweak layout generation
|
||||||
|
|
||||||
Camelot is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences. In some cases (such as `#170 <https://github.com/camelot-dev/camelot/issues/170>`_ and `#215 <https://github.com/camelot-dev/camelot/issues/215>`_), PDFMiner can group characters that should belong to the same sentence into separate sentences.
|
Camelot is built on top of PDFMiner's functionality of grouping characters on a page into words and sentences. In some cases (such as `#170 <https://github.com/camelot-dev/camelot/issues/170>`_ and `#215 <https://github.com/camelot-dev/camelot/issues/215>`_), PDFMiner can group characters that should belong to the same sentence into separate sentences.
|
||||||
|
|
||||||
To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ to improve layout generation, by passing the keyword arguments as a dict using ``layout_kwargs`` in :meth:`read_pdf() <camelot.read_pdf>`. To know more about the parameters you can tweak, you can check out `PDFMiner docs <https://euske.github.io/pdfminer/>`_.
|
To deal with such cases, you can tweak PDFMiner's `LAParams kwargs <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ to improve layout generation, by passing the keyword arguments as a dict using ``layout_kwargs`` in :meth:`read_pdf() <camelot.read_pdf>`. To know more about the parameters you can tweak, you can check out `PDFMiner docs <https://pdfminersix.rtfd.io/en/latest/reference/composable.html>`_.
|
||||||
|
|
||||||
::
|
::
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,56 @@
|
||||||
|
.. _faq:
|
||||||
|
|
||||||
|
Frequently Asked Questions
|
||||||
|
==========================
|
||||||
|
|
||||||
|
This part of the documentation answers some common questions. To add questions, please open an issue `here <https://github.com/camelot-dev/camelot/issues/new>`_.
|
||||||
|
|
||||||
|
Does Camelot work with image-based PDFs?
|
||||||
|
----------------------------------------
|
||||||
|
|
||||||
|
**No**, Camelot 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".)
|
||||||
|
|
||||||
|
How to reduce memory usage for long PDFs?
|
||||||
|
-----------------------------------------
|
||||||
|
|
||||||
|
During table extraction from long PDF documents, RAM usage can grow significantly.
|
||||||
|
|
||||||
|
A simple workaround is to divide the extraction into chunks, and save extracted data to disk at the end of every chunk.
|
||||||
|
|
||||||
|
For more details, check out this code snippet from `@anakin87 <https://github.com/anakin87>`_:
|
||||||
|
|
||||||
|
::
|
||||||
|
|
||||||
|
import camelot
|
||||||
|
|
||||||
|
|
||||||
|
def chunks(l, n):
|
||||||
|
"""Yield successive n-sized chunks from l."""
|
||||||
|
for i in range(0, len(l), n):
|
||||||
|
yield l[i : i + n]
|
||||||
|
|
||||||
|
|
||||||
|
def extract_tables(filepath, pages, chunks=50, export_path=".", params={}):
|
||||||
|
"""
|
||||||
|
Divide the extraction work into n chunks. At the end of every chunk,
|
||||||
|
save data on disk and free RAM.
|
||||||
|
|
||||||
|
filepath : str
|
||||||
|
Filepath or URL of the PDF file.
|
||||||
|
pages : str, optional (default: '1')
|
||||||
|
Comma-separated page numbers.
|
||||||
|
Example: '1,3,4' or '1,4-end' or 'all'.
|
||||||
|
"""
|
||||||
|
|
||||||
|
# get list of pages from camelot.handlers.PDFHandler
|
||||||
|
handler = camelot.handlers.PDFHandler(filepath)
|
||||||
|
page_list = handler._get_pages(filepath, pages=pages)
|
||||||
|
|
||||||
|
# chunk pages list
|
||||||
|
page_chunks = list(chunks(page_list, chunks))
|
||||||
|
|
||||||
|
# extraction and export
|
||||||
|
for chunk in page_chunks:
|
||||||
|
pages_string = str(chunk).replace("[", "").replace("]", "")
|
||||||
|
tables = camelot.read_pdf(filepath, pages=pages_string, **params)
|
||||||
|
tables.export(f"{export_path}/tables.csv")
|
||||||
|
|
@ -43,8 +43,9 @@ For Ubuntu/MacOS::
|
||||||
|
|
||||||
For Windows::
|
For Windows::
|
||||||
|
|
||||||
|
>>> import ctypes
|
||||||
>>> from ctypes.util import find_library
|
>>> from ctypes.util import find_library
|
||||||
>>> find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll"))
|
>>> find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll")))
|
||||||
<name-of-ghostscript-library-on-windows>
|
<name-of-ghostscript-library-on-windows>
|
||||||
|
|
||||||
**Check:** The output of the ``find_library`` function should not be empty.
|
**Check:** The output of the ``find_library`` function should not be empty.
|
||||||
|
|
|
||||||
104
setup.py
104
setup.py
|
|
@ -6,39 +6,38 @@ from setuptools import find_packages
|
||||||
|
|
||||||
here = os.path.abspath(os.path.dirname(__file__))
|
here = os.path.abspath(os.path.dirname(__file__))
|
||||||
about = {}
|
about = {}
|
||||||
with open(os.path.join(here, 'camelot', '__version__.py'), 'r') as f:
|
with open(os.path.join(here, "camelot", "__version__.py"), "r") as f:
|
||||||
exec(f.read(), about)
|
exec(f.read(), about)
|
||||||
|
|
||||||
with open('README.md', 'r') as f:
|
with open("README.md", "r") as f:
|
||||||
readme = f.read()
|
readme = f.read()
|
||||||
|
|
||||||
|
|
||||||
requires = [
|
requires = [
|
||||||
'chardet>=3.0.4',
|
"chardet>=3.0.4",
|
||||||
'click>=6.7',
|
"click>=6.7",
|
||||||
'numpy>=1.13.3',
|
"numpy>=1.13.3",
|
||||||
'openpyxl>=2.5.8',
|
"openpyxl>=2.5.8",
|
||||||
'pandas>=0.23.4',
|
"pandas>=0.23.4",
|
||||||
'pdfminer.six>=20200726',
|
"pdfminer.six>=20200726",
|
||||||
'PyPDF2>=1.26.0',
|
"PyPDF2>=1.26.0",
|
||||||
'tabulate'
|
"tabulate>=0.8.9",
|
||||||
]
|
]
|
||||||
|
|
||||||
cv_requires = [
|
cv_requires = ["opencv-python>=3.4.2.17"]
|
||||||
'opencv-python>=3.4.2.17'
|
|
||||||
]
|
|
||||||
|
|
||||||
plot_requires = [
|
plot_requires = [
|
||||||
'matplotlib>=2.2.3',
|
"matplotlib>=2.2.3",
|
||||||
]
|
]
|
||||||
|
|
||||||
dev_requires = [
|
dev_requires = [
|
||||||
'codecov>=2.0.15',
|
"codecov>=2.0.15",
|
||||||
'pytest>=5.4.3',
|
"pytest>=5.4.3",
|
||||||
'pytest-cov>=2.10.0',
|
"pytest-cov>=2.10.0",
|
||||||
'pytest-mpl>=0.11',
|
"pytest-mpl>=0.11",
|
||||||
'pytest-runner>=5.2',
|
"pytest-runner>=5.2",
|
||||||
'Sphinx>=3.1.2'
|
"Sphinx>=3.1.2",
|
||||||
|
"sphinx-autobuild>=2021.3.14",
|
||||||
]
|
]
|
||||||
|
|
||||||
all_requires = cv_requires + plot_requires
|
all_requires = cv_requires + plot_requires
|
||||||
|
|
@ -46,36 +45,39 @@ dev_requires = dev_requires + all_requires
|
||||||
|
|
||||||
|
|
||||||
def setup_package():
|
def setup_package():
|
||||||
metadata = dict(name=about['__title__'],
|
metadata = dict(
|
||||||
version=about['__version__'],
|
name=about["__title__"],
|
||||||
description=about['__description__'],
|
version=about["__version__"],
|
||||||
long_description=readme,
|
description=about["__description__"],
|
||||||
long_description_content_type="text/markdown",
|
long_description=readme,
|
||||||
url=about['__url__'],
|
long_description_content_type="text/markdown",
|
||||||
author=about['__author__'],
|
url=about["__url__"],
|
||||||
author_email=about['__author_email__'],
|
author=about["__author__"],
|
||||||
license=about['__license__'],
|
author_email=about["__author_email__"],
|
||||||
packages=find_packages(exclude=('tests',)),
|
license=about["__license__"],
|
||||||
install_requires=requires,
|
packages=find_packages(exclude=("tests",)),
|
||||||
extras_require={
|
install_requires=requires,
|
||||||
'all': all_requires,
|
extras_require={
|
||||||
'cv': cv_requires,
|
"all": all_requires,
|
||||||
'dev': dev_requires,
|
"cv": cv_requires,
|
||||||
'plot': plot_requires
|
"dev": dev_requires,
|
||||||
},
|
"plot": plot_requires,
|
||||||
entry_points={
|
},
|
||||||
'console_scripts': [
|
entry_points={
|
||||||
'camelot = camelot.cli:cli',
|
"console_scripts": [
|
||||||
],
|
"camelot = camelot.cli:cli",
|
||||||
},
|
],
|
||||||
classifiers=[
|
},
|
||||||
# Trove classifiers
|
classifiers=[
|
||||||
# Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
|
# Trove classifiers
|
||||||
'License :: OSI Approved :: MIT License',
|
# Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
|
||||||
'Programming Language :: Python :: 3.6',
|
"License :: OSI Approved :: MIT License",
|
||||||
'Programming Language :: Python :: 3.7',
|
"Programming Language :: Python :: 3.6",
|
||||||
'Programming Language :: Python :: 3.8'
|
"Programming Language :: Python :: 3.7",
|
||||||
])
|
"Programming Language :: Python :: 3.8",
|
||||||
|
"Programming Language :: Python :: 3.9",
|
||||||
|
],
|
||||||
|
)
|
||||||
|
|
||||||
try:
|
try:
|
||||||
from setuptools import setup
|
from setuptools import setup
|
||||||
|
|
@ -85,5 +87,5 @@ def setup_package():
|
||||||
setup(**metadata)
|
setup(**metadata)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == "__main__":
|
||||||
setup_package()
|
setup_package()
|
||||||
|
|
|
||||||
508
tests/data.py
508
tests/data.py
|
|
@ -2800,49 +2800,467 @@ data_stream_layout_kwargs = [
|
||||||
]
|
]
|
||||||
|
|
||||||
data_stream_duplicated_text = [
|
data_stream_duplicated_text = [
|
||||||
['', '2012 BETTER VARIETIES Harvest Report for Minnesota Central [ MNCE ]', '', '', '', '', '', '', '', '',
|
[
|
||||||
'ALL SEASON TEST'],
|
"",
|
||||||
['', 'Doug Toreen, Renville County, MN 55310 [ BIRD ISLAND ]', '', '', '', '', '', '', '', '',
|
"2012 BETTER VARIETIES Harvest Report for Minnesota Central [ MNCE ]",
|
||||||
'1.3 - 2.0 MAT. GROUP'],
|
"",
|
||||||
['PREV. CROP/HERB:', 'Corn / Surpass, Roundup', '', '', '', '', '', '', '', '', 'S2MNCE01'],
|
"",
|
||||||
['SOIL DESCRIPTION:', '', 'Canisteo clay loam, mod. well drained, non-irrigated', '', '', '', '', '', '', '', ''],
|
"",
|
||||||
['SOIL CONDITIONS:', '', 'High P, high K, 6.7 pH, 3.9% OM, Low SCN', '', '', '', '', '', '', '', '30" ROW SPACING'],
|
"",
|
||||||
['TILLAGE/CULTIVATION:', 'conventional w/ fall till', '', '', '', '', '', '', '', '', ''],
|
"",
|
||||||
['PEST MANAGEMENT:', 'Roundup twice', '', '', '', '', '', '', '', '', ''],
|
"",
|
||||||
['SEEDED - RATE:', 'May 15', '140 000 /A', '', '', '', '', '', '', 'TOP 30 for YIELD of 63 TESTED', ''],
|
"",
|
||||||
['HARVESTED - STAND:', 'Oct 3', '122 921 /A', '', '', '', '', '', '', 'AVERAGE of (3) REPLICATIONS', ''],
|
"",
|
||||||
['', '', '', '', 'SCN', 'Seed', 'Yield', 'Moisture', 'Lodging', 'Stand', 'Gross'],
|
"ALL SEASON TEST",
|
||||||
['Company/Brand', 'Product/Brand†', 'Technol.†', 'Mat.', 'Resist.', 'Trmt.†', 'Bu/A', '%', '%', '(x 1000)',
|
],
|
||||||
'Income'], ['Kruger', 'K2 1901', 'RR2Y', '1.9', 'R', 'Ac,PV', '56.4', '7.6', '0', '126.3', '$846'],
|
[
|
||||||
['Stine', '19RA02 §', 'RR2Y', '1.9', 'R', 'CMB', '55.3', '7.6', '0', '120.0', '$830'],
|
"",
|
||||||
['Wensman', 'W 3190NR2', 'RR2Y', '1.9', 'R', 'Ac', '54.5', '7.6', '0', '119.5', '$818'],
|
"Doug Toreen, Renville County, MN 55310 [ BIRD ISLAND ]",
|
||||||
['Hefty', 'H17Y12', 'RR2Y', '1.7', 'MR', 'I', '53.7', '7.7', '0', '124.4', '$806'],
|
"",
|
||||||
['Dyna-Gro', 'S15RY53', 'RR2Y', '1.5', 'R', 'Ac', '53.6', '7.7', '0', '126.8', '$804'],
|
"",
|
||||||
['LG Seeds', 'C2050R2', 'RR2Y', '2.1', 'R', 'Ac', '53.6', '7.7', '0', '123.9', '$804'],
|
"",
|
||||||
['Titan Pro', '19M42', 'RR2Y', '1.9', 'R', 'CMB', '53.6', '7.7', '0', '121.0', '$804'],
|
"",
|
||||||
['Stine', '19RA02 (2) §', 'RR2Y', '1.9', 'R', 'CMB', '53.4', '7.7', '0', '123.9', '$801'],
|
"",
|
||||||
['Asgrow', 'AG1832 §', 'RR2Y', '1.8', 'MR', 'Ac,PV', '52.9', '7.7', '0', '122.0', '$794'],
|
"",
|
||||||
['Prairie Brand', 'PB-1566R2', 'RR2Y', '1.5', 'R', 'CMB', '52.8', '7.7', '0', '122.9', '$792'],
|
"",
|
||||||
['Channel', '1901R2', 'RR2Y', '1.9', 'R', 'Ac,PV', '52.8', '7.6', '0', '123.4', '$791'],
|
"",
|
||||||
['Titan Pro', '20M1', 'RR2Y', '2.0', 'R', 'Am', '52.5', '7.5', '0', '124.4', '$788'],
|
"1.3 - 2.0 MAT. GROUP",
|
||||||
['Kruger', 'K2-2002', 'RR2Y', '2.0', 'R', 'Ac,PV', '52.4', '7.9', '0', '125.4', '$786'],
|
],
|
||||||
['Channel', '1700R2', 'RR2Y', '1.7', 'R', 'Ac,PV', '52.3', '7.9', '0', '123.9', '$784'],
|
[
|
||||||
['Hefty', 'H16Y11', 'RR2Y', '1.6', 'MR', 'I', '51.4', '7.6', '0', '123.9', '$771'],
|
"PREV. CROP/HERB:",
|
||||||
['Anderson', '162R2Y', 'RR2Y', '1.6', 'R', 'None', '51.3', '7.5', '0', '119.5', '$770'],
|
"Corn / Surpass, Roundup",
|
||||||
['Titan Pro', '15M22', 'RR2Y', '1.5', 'R', 'CMB', '51.3', '7.8', '0', '125.4', '$769'],
|
"",
|
||||||
['Dairyland', 'DSR-1710R2Y', 'RR2Y', '1.7', 'R', 'CMB', '51.3', '7.7', '0', '122.0', '$769'],
|
"",
|
||||||
['Hefty', 'H20R3', 'RR2Y', '2.0', 'MR', 'I', '50.5', '8.2', '0', '121.0', '$757'],
|
"",
|
||||||
['Prairie Brand', 'PB 1743R2', 'RR2Y', '1.7', 'R', 'CMB', '50.2', '7.7', '0', '125.8', '$752'],
|
"",
|
||||||
['Gold Country', '1741', 'RR2Y', '1.7', 'R', 'Ac', '50.1', '7.8', '0', '123.9', '$751'],
|
"",
|
||||||
['Trelay', '20RR43', 'RR2Y', '2.0', 'R', 'Ac,Ex', '49.9', '7.6', '0', '127.8', '$749'],
|
"",
|
||||||
['Hefty', 'H14R3', 'RR2Y', '1.4', 'MR', 'I', '49.7', '7.7', '0', '122.9', '$746'],
|
"",
|
||||||
['Prairie Brand', 'PB-2099NRR2', 'RR2Y', '2.0', 'R', 'CMB', '49.6', '7.8', '0', '126.3', '$743'],
|
"",
|
||||||
['Wensman', 'W 3174NR2', 'RR2Y', '1.7', 'R', 'Ac', '49.3', '7.6', '0', '122.5', '$740'],
|
"S2MNCE01",
|
||||||
['Kruger', 'K2 1602', 'RR2Y', '1.6', 'R', 'Ac,PV', '48.7', '7.6', '0', '125.4', '$731'],
|
],
|
||||||
['NK Brand', 'S18-C2 §', 'RR2Y', '1.8', 'R', 'CMB', '48.7', '7.7', '0', '126.8', '$731'],
|
[
|
||||||
['Kruger', 'K2 1902', 'RR2Y', '1.9', 'R', 'Ac,PV', '48.7', '7.5', '0', '124.4', '$730'],
|
"SOIL DESCRIPTION:",
|
||||||
['Prairie Brand', 'PB-1823R2', 'RR2Y', '1.8', 'R', 'None', '48.5', '7.6', '0', '121.0', '$727'],
|
"",
|
||||||
['Gold Country', '1541', 'RR2Y', '1.5', 'R', 'Ac', '48.4', '7.6', '0', '110.4', '$726'],
|
"Canisteo clay loam, mod. well drained, non-irrigated",
|
||||||
['', '', '', '', '', 'Test Average =', '47.6', '7.7', '0', '122.9', '$713'],
|
"",
|
||||||
['', '', '', '', '', 'LSD (0.10) =', '5.7', '0.3', 'ns', '37.8', '566.4']
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"SOIL CONDITIONS:",
|
||||||
|
"",
|
||||||
|
"High P, high K, 6.7 pH, 3.9% OM, Low SCN",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
'30" ROW SPACING',
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"TILLAGE/CULTIVATION:",
|
||||||
|
"conventional w/ fall till",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
],
|
||||||
|
["PEST MANAGEMENT:", "Roundup twice", "", "", "", "", "", "", "", "", ""],
|
||||||
|
[
|
||||||
|
"SEEDED - RATE:",
|
||||||
|
"May 15",
|
||||||
|
"140 000 /A",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"TOP 30 for YIELD of 63 TESTED",
|
||||||
|
"",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"HARVESTED - STAND:",
|
||||||
|
"Oct 3",
|
||||||
|
"122 921 /A",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"",
|
||||||
|
"AVERAGE of (3) REPLICATIONS",
|
||||||
|
"",
|
||||||
|
],
|
||||||
|
["", "", "", "", "SCN", "Seed", "Yield", "Moisture", "Lodging", "Stand", "Gross"],
|
||||||
|
[
|
||||||
|
"Company/Brand",
|
||||||
|
"Product/Brand†",
|
||||||
|
"Technol.†",
|
||||||
|
"Mat.",
|
||||||
|
"Resist.",
|
||||||
|
"Trmt.†",
|
||||||
|
"Bu/A",
|
||||||
|
"%",
|
||||||
|
"%",
|
||||||
|
"(x 1000)",
|
||||||
|
"Income",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Kruger",
|
||||||
|
"K2 1901",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"Ac,PV",
|
||||||
|
"56.4",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"126.3",
|
||||||
|
"$846",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Stine",
|
||||||
|
"19RA02 §",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"55.3",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"120.0",
|
||||||
|
"$830",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Wensman",
|
||||||
|
"W 3190NR2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"Ac",
|
||||||
|
"54.5",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"119.5",
|
||||||
|
"$818",
|
||||||
|
],
|
||||||
|
["Hefty", "H17Y12", "RR2Y", "1.7", "MR", "I", "53.7", "7.7", "0", "124.4", "$806"],
|
||||||
|
[
|
||||||
|
"Dyna-Gro",
|
||||||
|
"S15RY53",
|
||||||
|
"RR2Y",
|
||||||
|
"1.5",
|
||||||
|
"R",
|
||||||
|
"Ac",
|
||||||
|
"53.6",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"126.8",
|
||||||
|
"$804",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"LG Seeds",
|
||||||
|
"C2050R2",
|
||||||
|
"RR2Y",
|
||||||
|
"2.1",
|
||||||
|
"R",
|
||||||
|
"Ac",
|
||||||
|
"53.6",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"123.9",
|
||||||
|
"$804",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Titan Pro",
|
||||||
|
"19M42",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"53.6",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"121.0",
|
||||||
|
"$804",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Stine",
|
||||||
|
"19RA02 (2) §",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"53.4",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"123.9",
|
||||||
|
"$801",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Asgrow",
|
||||||
|
"AG1832 §",
|
||||||
|
"RR2Y",
|
||||||
|
"1.8",
|
||||||
|
"MR",
|
||||||
|
"Ac,PV",
|
||||||
|
"52.9",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"122.0",
|
||||||
|
"$794",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Prairie Brand",
|
||||||
|
"PB-1566R2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.5",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"52.8",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"122.9",
|
||||||
|
"$792",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Channel",
|
||||||
|
"1901R2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"Ac,PV",
|
||||||
|
"52.8",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"123.4",
|
||||||
|
"$791",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Titan Pro",
|
||||||
|
"20M1",
|
||||||
|
"RR2Y",
|
||||||
|
"2.0",
|
||||||
|
"R",
|
||||||
|
"Am",
|
||||||
|
"52.5",
|
||||||
|
"7.5",
|
||||||
|
"0",
|
||||||
|
"124.4",
|
||||||
|
"$788",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Kruger",
|
||||||
|
"K2-2002",
|
||||||
|
"RR2Y",
|
||||||
|
"2.0",
|
||||||
|
"R",
|
||||||
|
"Ac,PV",
|
||||||
|
"52.4",
|
||||||
|
"7.9",
|
||||||
|
"0",
|
||||||
|
"125.4",
|
||||||
|
"$786",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Channel",
|
||||||
|
"1700R2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.7",
|
||||||
|
"R",
|
||||||
|
"Ac,PV",
|
||||||
|
"52.3",
|
||||||
|
"7.9",
|
||||||
|
"0",
|
||||||
|
"123.9",
|
||||||
|
"$784",
|
||||||
|
],
|
||||||
|
["Hefty", "H16Y11", "RR2Y", "1.6", "MR", "I", "51.4", "7.6", "0", "123.9", "$771"],
|
||||||
|
[
|
||||||
|
"Anderson",
|
||||||
|
"162R2Y",
|
||||||
|
"RR2Y",
|
||||||
|
"1.6",
|
||||||
|
"R",
|
||||||
|
"None",
|
||||||
|
"51.3",
|
||||||
|
"7.5",
|
||||||
|
"0",
|
||||||
|
"119.5",
|
||||||
|
"$770",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Titan Pro",
|
||||||
|
"15M22",
|
||||||
|
"RR2Y",
|
||||||
|
"1.5",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"51.3",
|
||||||
|
"7.8",
|
||||||
|
"0",
|
||||||
|
"125.4",
|
||||||
|
"$769",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Dairyland",
|
||||||
|
"DSR-1710R2Y",
|
||||||
|
"RR2Y",
|
||||||
|
"1.7",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"51.3",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"122.0",
|
||||||
|
"$769",
|
||||||
|
],
|
||||||
|
["Hefty", "H20R3", "RR2Y", "2.0", "MR", "I", "50.5", "8.2", "0", "121.0", "$757"],
|
||||||
|
[
|
||||||
|
"Prairie Brand",
|
||||||
|
"PB 1743R2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.7",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"50.2",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"125.8",
|
||||||
|
"$752",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Gold Country",
|
||||||
|
"1741",
|
||||||
|
"RR2Y",
|
||||||
|
"1.7",
|
||||||
|
"R",
|
||||||
|
"Ac",
|
||||||
|
"50.1",
|
||||||
|
"7.8",
|
||||||
|
"0",
|
||||||
|
"123.9",
|
||||||
|
"$751",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Trelay",
|
||||||
|
"20RR43",
|
||||||
|
"RR2Y",
|
||||||
|
"2.0",
|
||||||
|
"R",
|
||||||
|
"Ac,Ex",
|
||||||
|
"49.9",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"127.8",
|
||||||
|
"$749",
|
||||||
|
],
|
||||||
|
["Hefty", "H14R3", "RR2Y", "1.4", "MR", "I", "49.7", "7.7", "0", "122.9", "$746"],
|
||||||
|
[
|
||||||
|
"Prairie Brand",
|
||||||
|
"PB-2099NRR2",
|
||||||
|
"RR2Y",
|
||||||
|
"2.0",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"49.6",
|
||||||
|
"7.8",
|
||||||
|
"0",
|
||||||
|
"126.3",
|
||||||
|
"$743",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Wensman",
|
||||||
|
"W 3174NR2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.7",
|
||||||
|
"R",
|
||||||
|
"Ac",
|
||||||
|
"49.3",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"122.5",
|
||||||
|
"$740",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Kruger",
|
||||||
|
"K2 1602",
|
||||||
|
"RR2Y",
|
||||||
|
"1.6",
|
||||||
|
"R",
|
||||||
|
"Ac,PV",
|
||||||
|
"48.7",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"125.4",
|
||||||
|
"$731",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"NK Brand",
|
||||||
|
"S18-C2 §",
|
||||||
|
"RR2Y",
|
||||||
|
"1.8",
|
||||||
|
"R",
|
||||||
|
"CMB",
|
||||||
|
"48.7",
|
||||||
|
"7.7",
|
||||||
|
"0",
|
||||||
|
"126.8",
|
||||||
|
"$731",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Kruger",
|
||||||
|
"K2 1902",
|
||||||
|
"RR2Y",
|
||||||
|
"1.9",
|
||||||
|
"R",
|
||||||
|
"Ac,PV",
|
||||||
|
"48.7",
|
||||||
|
"7.5",
|
||||||
|
"0",
|
||||||
|
"124.4",
|
||||||
|
"$730",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Prairie Brand",
|
||||||
|
"PB-1823R2",
|
||||||
|
"RR2Y",
|
||||||
|
"1.8",
|
||||||
|
"R",
|
||||||
|
"None",
|
||||||
|
"48.5",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"121.0",
|
||||||
|
"$727",
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"Gold Country",
|
||||||
|
"1541",
|
||||||
|
"RR2Y",
|
||||||
|
"1.5",
|
||||||
|
"R",
|
||||||
|
"Ac",
|
||||||
|
"48.4",
|
||||||
|
"7.6",
|
||||||
|
"0",
|
||||||
|
"110.4",
|
||||||
|
"$726",
|
||||||
|
],
|
||||||
|
["", "", "", "", "", "Test Average =", "47.6", "7.7", "0", "122.9", "$713"],
|
||||||
|
["", "", "", "", "", "LSD (0.10) =", "5.7", "0.3", "ns", "37.8", "566.4"],
|
||||||
]
|
]
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue