Merge pull request #2 from jahtz/dev

v2.0: Merge PageXML and Page class

MANIFEST.in

@@ -1,5 +1,4 @@
-recursive-include src/pypxml/resources *
-recursive-include src/pypxml *.py
+recursive-include src/pypxml *
 recursive-include src/cli *.py
 
 # Include the README and LICENSE files

README.md

@@ -15,101 +15,22 @@ pip install pypxml
 ```
 pypxml [OPTIONS] COMMAND [ARGS]...
 ```
-Coming in version 2.x
 
 ## API
 PyXML provides a feature rich Python API for working with PageXML files.
 
-### Basics
+### Example: Edit existing PageXML
 ```python
-from pypxml import PageXML, Page, Element, XMLType
+from pypxml import PageXML, PageType
 
 pxml = PageXML.from_xml('path_to_pagexml.xml')
-page1 = pxml.create_page(imageFilename='0001.png', 
-                         imageWidth=1000, 
-                         imageHeight=2500)
-page1.create_element(XMLType.TextRegion, id='ir01')
-pxml.to_xml('path_to_output.xml')
-```
-
-### PageXML class
-```python
-from pypxml import PageXML
-
-# open file
-pxml = PageXML.from_xml('path_to.xml')
-# or create new PageXML
-pxml = PageXML.new()
-
-# edit metadata
-pxml.creator = 'yourname'
-...
-
-# create a page
-page = pxml.create_page(imageFilename='0001.png',
-                        imageWidth=1000,
-                        imageHeight='2500')
-# or add existing page
-pxml.add_page(page)  # see below
-
-# iterate over pages
-for page in pxml:
-    ...
-
-# delete or modify pages
-pxml[0] = ...
-pxml.remove_page(pxml[1])
-
-# save object to file
-pxml.to_xml('output.xml')
-...
-```
+text_region = pxml.create_element(PageType.TextRegion, type='paragraph', id='tr_001')
+text_region.create_element(PageType.Coords, points='1,2 3,4 5,6 ...')
 
-### Page class
-```python
-from pypxml import Page, XMLType
-
-# create a page
-page = Page.new(imageFilename='0001.png',
-                imageWidth=1000,
-                imageHeight=2500)
-
-# modify attributes
-page['imageFilename'] = '0002.png'
-# or get element by index
-element = page[3]
-
-# add elements (automatically added to reading order if it is a region)
-text_region = page.create_element(XMLType.TextRegion, id='tr1')
-# or add existing element
-page.add_element(element)
-
-# iterate over regions
-for region in page:
-    ...
-...
-```
+for region in pxml.regions:
+    print(region.type)
 
-### Element class
-```python
-from pypxml import Element, XMLType
-
-# create an element
-coords = Element.new(XMLType.Coords, 
-                     points='1,2 3,4 5,6 7,8')
-# modify attributes
-coords['points'] = 'some other coords'
-# or get element by index
-baseline = text_region[2]
-
-# check if element is a region
-if text_region.is_region():
-    ...
-
-# get coords and baseline, if they exist
-coords = text_line.get_coords()
-baseline = text_line.get_baseline()
-...
+pxml.to_xml('path_to_output.xml')
 ```
 
 ## ZPD

pyproject.toml

@@ -6,9 +6,9 @@ build-backend = "setuptools.build_meta"
 name = "pypxml"
 description = "A python library for parsing, converting and modifying PageXML files. "
 keywords = ["PageXML", "XML", "OCR", "optical character recognition"]
-version = "1.0"
+version = "2.0"
 readme = "README.md"
-license = { file = "LICENSE" }
+license = { text = "MIT License" }
 authors = [
     { name="Janik Haitz", email="[email protected]" },
 ]

src/cli/pypxml_cli.py

@@ -3,8 +3,8 @@
 
 @click.group()
 @click.help_option('--help')
-@click.version_option('1.0', '--version',
-                      prog_name='PyPXML',
+@click.version_option('2.0', '--version',
+                      prog_name='pypxml',
                       message='%(prog)s v%(version)s - Developed at Centre for Philology and Digitality (ZPD), '
                               'University of Würzburg')
 def cli():

src/pypxml/__init__.py

@@ -2,8 +2,7 @@
 # Copyright (c) 2024 Janik Haitz
 # See the LICENSE file in the root directory for more details.
 
-from .pxml import PageXML
-from .page import Page
-from .element import Element
-from .resources.xml_schema import XMLSchema
-from .resources.xml_types import XMLType
+from .page_xml import PageXML
+from .page_element import PageElement
+from .page_types import PageType
+from .page_schema import PageSchema