ocrd_models.ocrd_page module

API to PAGE-XML, generated with generateDS from XML schema.

ocrd_models.ocrd_page.parse(inFileName, silence=False, print_warnings=True)[source]

Parse a file, create the object tree, and export it.

Parameters:
  • inFileName (str) –

  • print_warnings (boolean) –

Returns:

The root object in the tree.

ocrd_models.ocrd_page.parseEtree(inFileName, silence=False, print_warnings=True, mapping=None, nsmap=None)[source]

Parse a file, create the object tree, and export it. Return tree and mappings, too.

Parameters:
  • inFileName (str) –

  • print_warnings (boolean) –

Returns:

A tuple of
  • The root object in the tree.

  • The full node tree.

  • A mapping from object IDs to tree nodes.

  • A reverse mapping from tree nodes to object IDs.

ocrd_models.ocrd_page.parseString(inString, silence=False, print_warnings=True)[source]

Parse a string, create the object tree, and export it.

Parameters:

inString (str) –

Returns:

The root object in the tree.

ocrd_models.ocrd_page.OcrdPage

alias of PcGtsType

class ocrd_models.ocrd_page.AdvertRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, bgColour=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing advertisements. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The background colour of the region

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='AdvertRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='AdvertRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='AdvertRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='AdvertRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.AlternativeImageType(filename=None, comments=None, conf=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Confidence value (between 0 and 1)

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_filename()[source]
set_filename(filename)[source]
get_comments()[source]
set_comments(comments)[source]
get_conf()[source]
set_conf(conf)[source]
validate_ConfSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='AlternativeImageType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='AlternativeImageType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='AlternativeImageType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='AlternativeImageType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.BaselineType(points=None, conf=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Confidence value (between 0 and 1)

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_points()[source]
set_points(points)[source]
get_conf()[source]
set_conf(conf)[source]
validate_PointsType(value)[source]
validate_PointsType_patterns_ = [['^(([0-9]+,[0-9]+ )+([0-9]+,[0-9]+))$']]
validate_ConfSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='BaselineType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='BaselineType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='BaselineType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='BaselineType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.BorderType(Coords=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Border of the actual page (if the scanned image contains parts not belonging to the page).

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Coords()[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='BorderType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='BorderType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='BorderType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='BorderType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_Coords(Coords)[source]

Set coordinate polygon by given CoordsType object. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been cropped with a bbox of the previous polygon).

class ocrd_models.ocrd_page.ChartRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, type_=None, numColours=None, bgColour=None, embText=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing charts or graphs of any type, should be marked as chart regions. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The type of chart in the region An approximation of the number of colours used in the region The background colour of the region Specifies whether the region also contains text

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_type()[source]
set_type(type_)[source]
get_numColours()[source]
set_numColours(numColours)[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
get_embText()[source]
set_embText(embText)[source]
validate_ChartTypeSimpleType(value)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='ChartRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='ChartRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='ChartRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='ChartRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.ChemRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, bgColour=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing chemical formulas. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The background colour of the region

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='ChemRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='ChemRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='ChemRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='ChemRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.CoordsType(points=None, conf=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Polygon outline of the element as a path of points. No points may lie outside the outline of its parent, which in the case of Border is the bounding rectangle of the root image. Paths are closed by convention, i.e. the last point logically connects with the first (and at least 3 points are required to span an area). Paths must be planar (i.e. must not self-intersect). Confidence value (between 0 and 1)

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_points()[source]
get_conf()[source]
set_conf(conf)[source]
validate_PointsType(value)[source]
validate_PointsType_patterns_ = [['^(([0-9]+,[0-9]+ )+([0-9]+,[0-9]+))$']]
validate_ConfSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='CoordsType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='CoordsType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='CoordsType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='CoordsType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_points(points)[source]

Set coordinate polygon by given string. Moreover, invalidate the parent’s ``pc:AlternativeImage``s (because they will have been cropped with a bbox of the previous polygon).

class ocrd_models.ocrd_page.CustomRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, type_=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing content that is not covered by the default types (text, graphic, image, line drawing, chart, table, separator, maths, map, music, chem, advert, noise, unknown). Information on the type of content represented by this region

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_type()[source]
set_type(type_)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='CustomRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='CustomRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='CustomRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='CustomRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.GlyphType(id=None, ligature=None, symbol=None, script=None, production=None, custom=None, comments=None, AlternativeImage=None, Coords=None, Graphemes=None, TextEquiv=None, TextStyle=None, UserDefined=None, Labels=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

The script used for the glyph Overrides the production attribute of the parent word / text line / text region. For generic use

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_AlternativeImage()[source]
set_AlternativeImage(AlternativeImage)[source]
add_AlternativeImage(value)[source]
insert_AlternativeImage_at(index, value)[source]
replace_AlternativeImage_at(index, value)[source]
get_Coords()[source]
get_Graphemes()[source]
set_Graphemes(Graphemes)[source]
get_TextEquiv()[source]
set_TextEquiv(TextEquiv)[source]
add_TextEquiv(value)[source]
insert_TextEquiv_at(index, value)[source]
replace_TextEquiv_at(index, value)[source]
get_TextStyle()[source]
set_TextStyle(TextStyle)[source]
get_UserDefined()[source]
set_UserDefined(UserDefined)[source]
get_Labels()[source]
set_Labels(Labels)[source]
add_Labels(value)[source]
insert_Labels_at(index, value)[source]
replace_Labels_at(index, value)[source]
get_id()[source]
set_id(id)[source]
get_ligature()[source]
set_ligature(ligature)[source]
get_symbol()[source]
set_symbol(symbol)[source]
get_script()[source]
set_script(script)[source]
get_production()[source]
set_production(production)[source]
get_custom()[source]
set_custom(custom)[source]
get_comments()[source]
set_comments(comments)[source]
validate_ScriptSimpleType(value)[source]
validate_ProductionSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GlyphType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GlyphType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GlyphType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GlyphType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
invalidate_AlternativeImage(feature_selector=None)[source]

Remove derived images from this segment (due to changed coordinates).

If feature_selector is not none, remove only images with matching @comments, e.g. feature_selector=cropped,deskewed.

set_Coords(Coords)[source]

Set coordinate polygon by given CoordsType object. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been cropped with a bbox of the previous polygon).

class ocrd_models.ocrd_page.GraphemeBaseType(id=None, index=None, ligature=None, charType=None, custom=None, comments=None, TextEquiv=None, extensiontype_=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Base type for graphemes, grapheme groups and non-printing characters. Order index of grapheme, group, or non-printing character within the parent container (graphemes or glyph or grapheme group). Type of character represented by the grapheme, group, or non-printing character element. For generic useFor generic use

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_TextEquiv()[source]
set_TextEquiv(TextEquiv)[source]
add_TextEquiv(value)[source]
insert_TextEquiv_at(index, value)[source]
replace_TextEquiv_at(index, value)[source]
get_id()[source]
set_id(id)[source]
get_index()[source]
set_index(index)[source]
get_ligature()[source]
set_ligature(ligature)[source]
get_charType()[source]
set_charType(charType)[source]
get_custom()[source]
set_custom(custom)[source]
get_comments()[source]
set_comments(comments)[source]
get_extensiontype_()[source]
set_extensiontype_(extensiontype_)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemeBaseType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GraphemeBaseType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemeBaseType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GraphemeBaseType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.GraphemeGroupType(id=None, index=None, ligature=None, charType=None, custom=None, comments=None, TextEquiv=None, Grapheme=None, NonPrintingChar=None, gds_collector_=None, **kwargs_)[source]

Bases: GraphemeBaseType

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of GraphemeBaseType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Grapheme()[source]
set_Grapheme(Grapheme)[source]
add_Grapheme(value)[source]
insert_Grapheme_at(index, value)[source]
replace_Grapheme_at(index, value)[source]
get_NonPrintingChar()[source]
set_NonPrintingChar(NonPrintingChar)[source]
add_NonPrintingChar(value)[source]
insert_NonPrintingChar_at(index, value)[source]
replace_NonPrintingChar_at(index, value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemeGroupType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GraphemeGroupType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemeGroupType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GraphemeGroupType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.GraphemeType(id=None, index=None, ligature=None, charType=None, custom=None, comments=None, TextEquiv=None, Coords=None, gds_collector_=None, **kwargs_)[source]

Bases: GraphemeBaseType

Represents a sub-element of a glyph. Smallest graphical unit that can be assigned a Unicode code point.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of GraphemeBaseType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Coords()[source]
set_Coords(Coords)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemeType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GraphemeType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemeType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GraphemeType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.GraphemesType(Grapheme=None, NonPrintingChar=None, GraphemeGroup=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Container for graphemes, grapheme groups and non-printing characters.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Grapheme()[source]
set_Grapheme(Grapheme)[source]
add_Grapheme(value)[source]
insert_Grapheme_at(index, value)[source]
replace_Grapheme_at(index, value)[source]
get_NonPrintingChar()[source]
set_NonPrintingChar(NonPrintingChar)[source]
add_NonPrintingChar(value)[source]
insert_NonPrintingChar_at(index, value)[source]
replace_NonPrintingChar_at(index, value)[source]
get_GraphemeGroup()[source]
set_GraphemeGroup(GraphemeGroup)[source]
add_GraphemeGroup(value)[source]
insert_GraphemeGroup_at(index, value)[source]
replace_GraphemeGroup_at(index, value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemesType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GraphemesType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GraphemesType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GraphemesType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.GraphicRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, type_=None, numColours=None, embText=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing simple graphics, such as a company logo, should be marked as graphic regions. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The type of graphic in the region An approximation of the number of colours used in the region Specifies whether the region also contains text.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_type()[source]
set_type(type_)[source]
get_numColours()[source]
set_numColours(numColours)[source]
get_embText()[source]
set_embText(embText)[source]
validate_GraphicsTypeSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='GraphicRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GraphicRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='GraphicRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GraphicRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.GridPointsType(index=None, points=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Points with x,y coordinates. The grid row index

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_index()[source]
set_index(index)[source]
get_points()[source]
set_points(points)[source]
validate_PointsType(value)[source]
validate_PointsType_patterns_ = [['^(([0-9]+,[0-9]+ )+([0-9]+,[0-9]+))$']]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GridPointsType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GridPointsType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GridPointsType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GridPointsType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.GridType(GridPoints=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Matrix of grid points defining the table grid on the page.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_GridPoints()[source]
set_GridPoints(GridPoints)[source]
add_GridPoints(value)[source]
insert_GridPoints_at(index, value)[source]
replace_GridPoints_at(index, value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GridType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='GridType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='GridType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='GridType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.ImageRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, colourDepth=None, bgColour=None, embText=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

An image is considered to be more intricate and complex than a graphic. These can be photos or drawings. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The colour bit depth required for the region The background colour of the region Specifies whether the region also contains text

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_colourDepth()[source]
set_colourDepth(colourDepth)[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
get_embText()[source]
set_embText(embText)[source]
validate_ColourDepthSimpleType(value)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='ImageRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='ImageRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='ImageRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='ImageRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.LabelType(value=None, type_=None, comments=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Semantic label The label / tag (e.g. ‘person’). Can be an RDF resource identifier (e.g. object of an RDF triple). Additional information on the label (e.g. ‘YYYY-mm-dd’ for a date label). Can be used as predicate of an RDF triple.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_value()[source]
set_value(value)[source]
get_type()[source]
set_type(type_)[source]
get_comments()[source]
set_comments(comments)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LabelType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='LabelType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LabelType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='LabelType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.LabelsType(externalModel=None, externalId=None, prefix=None, comments=None, Label=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Reference to external model / ontology / schema E.g. an RDF resource identifier (to be used as subject or object of an RDF triple) Prefix for all labels (e.g. first part of an URI)

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Label()[source]
set_Label(Label)[source]
add_Label(value)[source]
insert_Label_at(index, value)[source]
replace_Label_at(index, value)[source]
get_externalModel()[source]
set_externalModel(externalModel)[source]
get_externalId()[source]
set_externalId(externalId)[source]
get_prefix()[source]
set_prefix(prefix)[source]
get_comments()[source]
set_comments(comments)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LabelsType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='LabelsType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LabelsType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='LabelsType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.LayerType(id=None, zIndex=None, caption=None, RegionRef=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_RegionRef()[source]
set_RegionRef(RegionRef)[source]
add_RegionRef(value)[source]
insert_RegionRef_at(index, value)[source]
replace_RegionRef_at(index, value)[source]
get_id()[source]
set_id(id)[source]
get_zIndex()[source]
set_zIndex(zIndex)[source]
get_caption()[source]
set_caption(caption)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LayerType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='LayerType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LayerType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='LayerType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.LayersType(Layer=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Can be used to express the z-index of overlapping regions. An element with a greater z-index is always in front of another element with lower z-index.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Layer()[source]
set_Layer(Layer)[source]
add_Layer(value)[source]
insert_Layer_at(index, value)[source]
replace_Layer_at(index, value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LayersType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='LayersType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='LayersType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='LayersType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.LineDrawingRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, penColour=None, bgColour=None, embText=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

A line drawing is a single colour illustration without solid areas. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The pen (foreground) colour of the region The background colour of the region Specifies whether the region also contains text

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_penColour()[source]
set_penColour(penColour)[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
get_embText()[source]
set_embText(embText)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='LineDrawingRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='LineDrawingRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='LineDrawingRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='LineDrawingRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.MapRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing maps. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='MapRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='MapRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='MapRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='MapRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.MathsRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, bgColour=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing equations and mathematical symbols should be marked as maths regions. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The background colour of the region

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='MathsRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='MathsRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='MathsRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='MathsRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.MetadataItemType(type_=None, name=None, value=None, date=None, Labels=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Type of metadata (e.g. author) E.g. imagePhotometricInterpretation E.g. RGB

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Labels()[source]
set_Labels(Labels)[source]
add_Labels(value)[source]
insert_Labels_at(index, value)[source]
replace_Labels_at(index, value)[source]
get_type()[source]
set_type(type_)[source]
get_name()[source]
set_name(name)[source]
get_value()[source]
set_value(value)[source]
get_date()[source]
set_date(date)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='MetadataItemType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='MetadataItemType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='MetadataItemType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='MetadataItemType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.MetadataType(externalRef=None, Creator=None, Created=None, LastChange=None, Comments=None, UserDefined=None, MetadataItem=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

External reference of any kind

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Creator()[source]
set_Creator(Creator)[source]
get_Created()[source]
set_Created(Created)[source]
get_LastChange()[source]
set_LastChange(LastChange)[source]
get_Comments()[source]
set_Comments(Comments)[source]
get_UserDefined()[source]
set_UserDefined(UserDefined)[source]
get_MetadataItem()[source]
set_MetadataItem(MetadataItem)[source]
add_MetadataItem(value)[source]
insert_MetadataItem_at(index, value)[source]
replace_MetadataItem_at(index, value)[source]
get_externalRef()[source]
set_externalRef(externalRef)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15" xmlns:None="http://www.w3.org/2001/XMLSchema" ', name_='MetadataType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='MetadataType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15" xmlns:None="http://www.w3.org/2001/XMLSchema" ', name_='MetadataType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='MetadataType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.MusicRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, orientation=None, bgColour=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Regions containing musical notations. The angle the rectangle encapsulating a region has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). Range: -179.999,180 The background colour of the region

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_orientation()[source]
get_bgColour()[source]
set_bgColour(bgColour)[source]
validate_ColourSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='MusicRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='MusicRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='MusicRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='MusicRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.NoiseRegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, gds_collector_=None, **kwargs_)[source]

Bases: RegionType

Noise regions are regions where no real data lies, only false data created by artifacts on the document or scanner noise.

member_data_items_ = []
subclass = None
superclass

alias of RegionType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='', name_='NoiseRegionType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='NoiseRegionType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='', name_='NoiseRegionType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='NoiseRegionType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.NonPrintingCharType(id=None, index=None, ligature=None, charType=None, custom=None, comments=None, TextEquiv=None, gds_collector_=None, **kwargs_)[source]

Bases: GraphemeBaseType

A glyph component without visual representation but with Unicode code point. Non-visual / non-printing / control character. Part of grapheme container (of glyph) or grapheme sub group.

member_data_items_ = []
subclass = None
superclass

alias of GraphemeBaseType

static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='NonPrintingCharType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='NonPrintingCharType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='NonPrintingCharType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='NonPrintingCharType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.OrderedGroupIndexedType(id=None, regionRef=None, index=None, caption=None, type_=None, continuation=None, custom=None, comments=None, UserDefined=None, Labels=None, RegionRefIndexed=None, OrderedGroupIndexed=None, UnorderedGroupIndexed=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Indexed group containing ordered elements Optional link to a parent region of nested regions. The parent region doubles as reading order group. Only the nested regions should be allowed as group members. Position (order number) of this item within the current hierarchy level. Is this group a continuation of another group (from previous column or page, for example)? For generic use

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_UserDefined()[source]
set_UserDefined(UserDefined)[source]
get_Labels()[source]
set_Labels(Labels)[source]
add_Labels(value)[source]
insert_Labels_at(index, value)[source]
replace_Labels_at(index, value)[source]
get_RegionRefIndexed()[source]
set_RegionRefIndexed(RegionRefIndexed)[source]
add_RegionRefIndexed(value)[source]
insert_RegionRefIndexed_at(index, value)[source]
replace_RegionRefIndexed_at(index, value)[source]
get_OrderedGroupIndexed()[source]
set_OrderedGroupIndexed(OrderedGroupIndexed)[source]
add_OrderedGroupIndexed(value)[source]
insert_OrderedGroupIndexed_at(index, value)[source]
replace_OrderedGroupIndexed_at(index, value)[source]
get_UnorderedGroupIndexed()[source]
set_UnorderedGroupIndexed(UnorderedGroupIndexed)[source]
add_UnorderedGroupIndexed(value)[source]
insert_UnorderedGroupIndexed_at(index, value)[source]
replace_UnorderedGroupIndexed_at(index, value)[source]
get_id()[source]
set_id(id)[source]
get_regionRef()[source]
set_regionRef(regionRef)[source]
get_index()[source]
set_index(index)[source]
get_caption()[source]
set_caption(caption)[source]
get_type()[source]
set_type(type_)[source]
get_continuation()[source]
set_continuation(continuation)[source]
get_custom()[source]
set_custom(custom)[source]
get_comments()[source]
set_comments(comments)[source]
validate_GroupTypeSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='OrderedGroupIndexedType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='OrderedGroupIndexedType')[source]
to_etree(parent_element=None, name_='OrderedGroupIndexedType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
get_AllIndexed(classes=None, index_sort=True)[source]

Get all indexed children sorted by their @index.

Parameters:
  • classes (list) – Type of children (sans Indexed) to return. Default: ['RegionRef', 'OrderedGroup', 'UnorderedGroup']

  • index_sort (boolean) – Whether to sort by @index

Returns:

a list of RegionRefIndexedType, OrderedGroupIndexedType, and UnorderedGroupIndexedType

clear_AllIndexed()[source]
extend_AllIndexed(elements, validate_continuity=False)[source]

Add all elements in list elements, respecting @index order. With validate_continuity, check that all new elements come after all old elements (or raise an exception). Otherwise, ensure this condition silently (by increasing @index accordingly).

sort_AllIndexed(validate_uniqueness=True)[source]

Sort all indexed children in-place.

exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='OrderedGroupType', fromsubclass_=False, pretty_print=True)[source]
class ocrd_models.ocrd_page.OrderedGroupType(id=None, regionRef=None, caption=None, type_=None, continuation=None, custom=None, comments=None, UserDefined=None, Labels=None, RegionRefIndexed=None, OrderedGroupIndexed=None, UnorderedGroupIndexed=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Numbered group (contains ordered elements) Optional link to a parent region of nested regions. The parent region doubles as reading order group. Only the nested regions should be allowed as group members. Is this group a continuation of another group (from previous column or page, for example)? For generic use

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_UserDefined()[source]
set_UserDefined(UserDefined)[source]
get_Labels()[source]
set_Labels(Labels)[source]
add_Labels(value)[source]
insert_Labels_at(index, value)[source]
replace_Labels_at(index, value)[source]
get_RegionRefIndexed()[source]
set_RegionRefIndexed(RegionRefIndexed)[source]
add_RegionRefIndexed(value)[source]
insert_RegionRefIndexed_at(index, value)[source]
replace_RegionRefIndexed_at(index, value)[source]
get_OrderedGroupIndexed()[source]
set_OrderedGroupIndexed(OrderedGroupIndexed)[source]
add_OrderedGroupIndexed(value)[source]
insert_OrderedGroupIndexed_at(index, value)[source]
replace_OrderedGroupIndexed_at(index, value)[source]
get_UnorderedGroupIndexed()[source]
set_UnorderedGroupIndexed(UnorderedGroupIndexed)[source]
add_UnorderedGroupIndexed(value)[source]
insert_UnorderedGroupIndexed_at(index, value)[source]
replace_UnorderedGroupIndexed_at(index, value)[source]
get_id()[source]
set_id(id)[source]
get_regionRef()[source]
set_regionRef(regionRef)[source]
get_caption()[source]
set_caption(caption)[source]
get_type()[source]
set_type(type_)[source]
get_continuation()[source]
set_continuation(continuation)[source]
get_custom()[source]
set_custom(custom)[source]
get_comments()[source]
set_comments(comments)[source]
validate_GroupTypeSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='OrderedGroupType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='OrderedGroupType')[source]
to_etree(parent_element=None, name_='OrderedGroupType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
get_AllIndexed(classes=None, index_sort=True)[source]

Get all indexed children sorted by their @index.

Parameters:
  • classes (list) – Type of children (sans Indexed) to return. Default: ['RegionRef', 'OrderedGroup', 'UnorderedGroup']

  • index_sort (boolean) – Whether to sort by @index

Returns:

a list of RegionRefIndexedType, OrderedGroupIndexedType, and UnorderedGroupIndexedType

clear_AllIndexed()[source]
extend_AllIndexed(elements, validate_continuity=False)[source]

Add all elements in list elements, respecting @index order. With validate_continuity, check that all new elements come after all old elements (or raise an exception). Otherwise, ensure this condition silently (by increasing @index accordingly).

sort_AllIndexed(validate_uniqueness=True)[source]

Sort all indexed children in-place.

exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='OrderedGroupType', fromsubclass_=False, pretty_print=True)[source]
class ocrd_models.ocrd_page.PageType(imageFilename=None, imageWidth=None, imageHeight=None, imageXResolution=None, imageYResolution=None, imageResolutionUnit=None, custom=None, orientation=None, type_=None, primaryLanguage=None, secondaryLanguage=None, primaryScript=None, secondaryScript=None, readingDirection=None, textLineOrder=None, conf=None, AlternativeImage=None, Border=None, PrintSpace=None, ReadingOrder=None, Layers=None, Relations=None, TextStyle=None, UserDefined=None, Labels=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, MapRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Contains the image file name including the file extension. Specifies the width of the image.Specifies the height of the image.Specifies the image resolution in width.Specifies the image resolution in height. Specifies the unit of the resolution information referring to a standardised unit of measurement (pixels per inch, pixels per centimeter or other). For generic use The angle the rectangle encapsulating the page (or its Border) has to be rotated in clockwise direction in order to correct the present skew (negative values indicate anti-clockwise rotation). (The rotated image can be further referenced via “AlternativeImage”.) Range: -179.999,180 The type of the page within the document (e.g. cover page). The primary language used in the page (lower-level definitions override the page-level definition). The secondary language used in the page (lower-level definitions override the page-level definition). The primary script used in the page (lower-level definitions override the page-level definition). The secondary script used in the page (lower-level definitions override the page-level definition). The direction in which text within lines should be read (order of words and characters), in addition to “textLineOrder” (lower-level definitions override the page-level definition). The order of text lines within a block, in addition to “readingDirection” (lower-level definitions override the page-level definition). Confidence value for whole page (between 0 and 1)

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_AlternativeImage()[source]
set_AlternativeImage(AlternativeImage)[source]
add_AlternativeImage(value)[source]
insert_AlternativeImage_at(index, value)[source]
replace_AlternativeImage_at(index, value)[source]
get_Border()[source]
get_PrintSpace()[source]
set_PrintSpace(PrintSpace)[source]
get_ReadingOrder()[source]
set_ReadingOrder(ReadingOrder)[source]
get_Layers()[source]
set_Layers(Layers)[source]
get_Relations()[source]
set_Relations(Relations)[source]
get_TextStyle()[source]
set_TextStyle(TextStyle)[source]
get_UserDefined()[source]
set_UserDefined(UserDefined)[source]
get_Labels()[source]
set_Labels(Labels)[source]
add_Labels(value)[source]
insert_Labels_at(index, value)[source]
replace_Labels_at(index, value)[source]
get_TextRegion()[source]
set_TextRegion(TextRegion)[source]
add_TextRegion(value)[source]
insert_TextRegion_at(index, value)[source]
replace_TextRegion_at(index, value)[source]
get_ImageRegion()[source]
set_ImageRegion(ImageRegion)[source]
add_ImageRegion(value)[source]
insert_ImageRegion_at(index, value)[source]
replace_ImageRegion_at(index, value)[source]
get_LineDrawingRegion()[source]
set_LineDrawingRegion(LineDrawingRegion)[source]
add_LineDrawingRegion(value)[source]
insert_LineDrawingRegion_at(index, value)[source]
replace_LineDrawingRegion_at(index, value)[source]
get_GraphicRegion()[source]
set_GraphicRegion(GraphicRegion)[source]
add_GraphicRegion(value)[source]
insert_GraphicRegion_at(index, value)[source]
replace_GraphicRegion_at(index, value)[source]
get_TableRegion()[source]
set_TableRegion(TableRegion)[source]
add_TableRegion(value)[source]
insert_TableRegion_at(index, value)[source]
replace_TableRegion_at(index, value)[source]
get_ChartRegion()[source]
set_ChartRegion(ChartRegion)[source]
add_ChartRegion(value)[source]
insert_ChartRegion_at(index, value)[source]
replace_ChartRegion_at(index, value)[source]
get_MapRegion()[source]
set_MapRegion(MapRegion)[source]
add_MapRegion(value)[source]
insert_MapRegion_at(index, value)[source]
replace_MapRegion_at(index, value)[source]
get_SeparatorRegion()[source]
set_SeparatorRegion(SeparatorRegion)[source]
add_SeparatorRegion(value)[source]
insert_SeparatorRegion_at(index, value)[source]
replace_SeparatorRegion_at(index, value)[source]
get_MathsRegion()[source]
set_MathsRegion(MathsRegion)[source]
add_MathsRegion(value)[source]
insert_MathsRegion_at(index, value)[source]
replace_MathsRegion_at(index, value)[source]
get_ChemRegion()[source]
set_ChemRegion(ChemRegion)[source]
add_ChemRegion(value)[source]
insert_ChemRegion_at(index, value)[source]
replace_ChemRegion_at(index, value)[source]
get_MusicRegion()[source]
set_MusicRegion(MusicRegion)[source]
add_MusicRegion(value)[source]
insert_MusicRegion_at(index, value)[source]
replace_MusicRegion_at(index, value)[source]
get_AdvertRegion()[source]
set_AdvertRegion(AdvertRegion)[source]
add_AdvertRegion(value)[source]
insert_AdvertRegion_at(index, value)[source]
replace_AdvertRegion_at(index, value)[source]
get_NoiseRegion()[source]
set_NoiseRegion(NoiseRegion)[source]
add_NoiseRegion(value)[source]
insert_NoiseRegion_at(index, value)[source]
replace_NoiseRegion_at(index, value)[source]
get_UnknownRegion()[source]
set_UnknownRegion(UnknownRegion)[source]
add_UnknownRegion(value)[source]
insert_UnknownRegion_at(index, value)[source]
replace_UnknownRegion_at(index, value)[source]
get_CustomRegion()[source]
set_CustomRegion(CustomRegion)[source]
add_CustomRegion(value)[source]
insert_CustomRegion_at(index, value)[source]
replace_CustomRegion_at(index, value)[source]
get_imageFilename()[source]
set_imageFilename(imageFilename)[source]
get_imageWidth()[source]
set_imageWidth(imageWidth)[source]
get_imageHeight()[source]
set_imageHeight(imageHeight)[source]
get_imageXResolution()[source]
set_imageXResolution(imageXResolution)[source]
get_imageYResolution()[source]
set_imageYResolution(imageYResolution)[source]
get_imageResolutionUnit()[source]
set_imageResolutionUnit(imageResolutionUnit)[source]
get_custom()[source]
set_custom(custom)[source]
get_orientation()[source]
get_type()[source]
set_type(type_)[source]
get_primaryLanguage()[source]
set_primaryLanguage(primaryLanguage)[source]
get_secondaryLanguage()[source]
set_secondaryLanguage(secondaryLanguage)[source]
get_primaryScript()[source]
set_primaryScript(primaryScript)[source]
get_secondaryScript()[source]
set_secondaryScript(secondaryScript)[source]
get_readingDirection()[source]
set_readingDirection(readingDirection)[source]
get_textLineOrder()[source]
set_textLineOrder(textLineOrder)[source]
get_conf()[source]
set_conf(conf)[source]
validate_PageTypeSimpleType(value)[source]
validate_LanguageSimpleType(value)[source]
validate_ScriptSimpleType(value)[source]
validate_ReadingDirectionSimpleType(value)[source]
validate_TextLineOrderSimpleType(value)[source]
validate_ConfSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='PageType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='PageType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='PageType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='PageType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
property id
get_AllRegions(classes=None, order='document', depth=0)[source]

Get all the *Region elements, or only those provided by classes. Return in document order, unless order is reading-order.

Parameters:
  • classes (list) – Classes of regions that shall be returned, e.g. ['Text', 'Image']

  • order ("document"|"reading-order"|"reading-order-only") – Whether to return regions sorted by document order (document, default) or by reading order with regions not in the reading order at the end of the returned list (reading-order) or regions not in the reading order omitted (reading-order-only)

  • depth (int) – Recursive depth to look for regions at, set to 0 for all regions at any depth. Default: 0

Returns:

a list of TextRegionType, ImageRegionType, LineDrawingRegionType, GraphicRegionType, TableRegionType, ChartRegionType, MapRegionType, SeparatorRegionType, MathsRegionType, ChemRegionType, MusicRegionType, AdvertRegionType, NoiseRegionType, UnknownRegionType, and/or CustomRegionType

For example, to get all text anywhere on the page in reading order, use:

'\n'.join(line.get_TextEquiv()[0].Unicode
          for region in page.get_AllRegions(classes=['Text'], depth=0, order='reading-order')
          for line in region.get_TextLine())
get_AllAlternativeImages(page=True, region=True, line=True, word=True, glyph=True)[source]

Get all the pc:AlternativeImage in a document

Parameters:
  • page (boolean) – Get images on pc:Page level

  • region (boolean) – Get images on pc:*Region level

  • line (boolean) – Get images on pc:TextLine level

  • word (boolean) – Get images on pc:Word level

  • glyph (boolean) – Get images on pc:Glyph level

Returns:

a list of AlternativeImageType

invalidate_AlternativeImage(feature_selector=None)[source]

Remove derived images from this segment (due to changed coordinates).

If feature_selector is not none, remove only images with matching @comments, e.g. feature_selector=cropped,deskewed.

set_Border(Border)[source]

Set coordinate polygon by given BorderType object. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been cropped with a bbox of the previous polygon).

get_AllTextLines(region_order='document', respect_textline_order=True)[source]

Return all the TextLine in the document

Parameters:
  • region_order ("document"|"reading-order"|"reading-order-only") – Whether to return regions sorted by document order (document, default) or by reading order with regions not in the reading order at the end of the returned list (reading-order) or regions not in the reading order omitted (reading-order-only)

  • respect_textline_order (boolean) – Whether to respect @textLineOrder attribute

Returns:

a list of TextLineType

set_orientation(orientation)[source]

Set deskewing angle to given orientation number. Moreover, invalidate self’s ``pc:AlternativeImage``s (because they will have been rotated and enlarged with the angle of the previous value).

class ocrd_models.ocrd_page.PcGtsType(pcGtsId=None, Metadata=None, Page=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Metadata()[source]
set_Metadata(Metadata)[source]
get_Page()[source]
set_Page(Page)[source]
get_pcGtsId()[source]
set_pcGtsId(pcGtsId)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='PcGtsType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='PcGtsType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='PcGtsType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='PcGtsType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
property id
get_AllAlternativeImagePaths(page=True, region=True, line=True, word=True, glyph=True)[source]

Get all the pc:AlternativeImage/@filename paths referenced in the PAGE-XML document.

Parameters:
  • page (boolean) – Get images on pc:Page level

  • region (boolean) – Get images on pc:*Region level

  • line (boolean) – Get images on pc:TextLine level

  • word (boolean) – Get images on pc:Word level

  • glyph (boolean) – Get images on pc:Glyph level

Returns:

a list of image filename strings

prune_ReadingOrder()[source]

Remove any empty ReadingOrder elements

class ocrd_models.ocrd_page.PrintSpaceType(Coords=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Determines the effective area on the paper of a printed page. Its size is equal for all pages of a book (exceptions: titlepage, multipage pictures). It contains all living elements (except marginals) like body type, footnotes, headings, running titles. It does not contain pagenumber (if not part of running title), marginals, signature mark, preview words.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_Coords()[source]
set_Coords(Coords)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='PrintSpaceType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='PrintSpaceType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='PrintSpaceType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='PrintSpaceType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.ReadingOrderType(conf=None, OrderedGroup=None, UnorderedGroup=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Definition of the reading order within the page. To express a reading order between elements they have to be included in an OrderedGroup. Groups may contain further groups. Confidence value (between 0 and 1)

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_OrderedGroup()[source]
set_OrderedGroup(OrderedGroup)[source]
get_UnorderedGroup()[source]
set_UnorderedGroup(UnorderedGroup)[source]
get_conf()[source]
set_conf(conf)[source]
validate_ConfSimpleType(value)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='ReadingOrderType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='ReadingOrderType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='ReadingOrderType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='ReadingOrderType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.RegionRefIndexedType(index=None, regionRef=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

Numbered regionPosition (order number) of this item within the current hierarchy level.

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_index()[source]
set_index(index)[source]
get_regionRef()[source]
set_regionRef(regionRef)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='RegionRefIndexedType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='RegionRefIndexedType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='RegionRefIndexedType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='RegionRefIndexedType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.RegionRefType(regionRef=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_regionRef()[source]
set_regionRef(regionRef)[source]
hasContent_()[source]
export(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='RegionRefType', pretty_print=True)[source]
exportAttributes(outfile, level, already_processed, namespaceprefix_='', name_='RegionRefType')[source]
exportChildren(outfile, level, namespaceprefix_='', namespacedef_='xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15"', name_='RegionRefType', fromsubclass_=False, pretty_print=True)[source]
to_etree(parent_element=None, name_='RegionRefType', mapping_=None, nsmap_=None)[source]
build(node, gds_collector_=None)[source]
buildAttributes(node, attrs, already_processed)[source]
buildChildren(child_, node, nodeName_, fromsubclass_=False, gds_collector_=None)[source]
class ocrd_models.ocrd_page.RegionType(id=None, custom=None, comments=None, continuation=None, AlternativeImage=None, Coords=None, UserDefined=None, Labels=None, Roles=None, TextRegion=None, ImageRegion=None, LineDrawingRegion=None, GraphicRegion=None, TableRegion=None, ChartRegion=None, SeparatorRegion=None, MathsRegion=None, ChemRegion=None, MusicRegion=None, AdvertRegion=None, NoiseRegion=None, UnknownRegion=None, CustomRegion=None, extensiontype_=None, gds_collector_=None, **kwargs_)[source]

Bases: GeneratedsSuper

For generic use Is this region a continuation of another region (in previous column or page, for example)?

member_data_items_ = [<ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>, <ocrd_models.ocrd_page_generateds.MemberSpec_ object>]
subclass = None
superclass = None
static factory(*args_, **kwargs_)[source]
get_ns_prefix_()[source]
set_ns_prefix_(ns_prefix)[source]
get_AlternativeImage()[source]
set_AlternativeImage(AlternativeImage)[source]
add_AlternativeImage(value)[source]
insert_AlternativeImage_at(index, value)[source]
replace_AlternativeImage_at(index, value)[source]
get_Coords()[source]
get_UserDefined()[source]
set_UserDefined(UserDefined)[source]
get_Labels()[source]
set_Labels(Labels)[source]
add_Labels(value)[source]
insert_Labels_at(index, value)[source]
replace_Labels_at(index, value)[source]
get_Roles()[source]
set_Roles(Roles)[source]
get_TextRegion()[source]
set_TextRegion(TextRegion)[source]
add_TextRegion(value)[source]
insert_TextRegion_at(index, value)[source]
replace_TextRegion_at(index, value)[source]
get_ImageRegion()[source]
set_ImageRegion(ImageRegion)[source]
add_ImageRegion(value)[source]
insert_ImageRegion_at(index, value)[source]
replace_ImageRegion_at(index, value)[source]
get_LineDrawingRegion()[source]
set_LineDrawingRegion(LineDrawingRegion)[source]
add_LineDrawingRegion(value)[source]
insert_LineDrawingRegion_at(index, value)[source]
replace_LineDrawingRegion_at(index, value)[source]
get_GraphicRegion()[source]
set_GraphicRegion(GraphicRegion)[source]
add_GraphicRegion(value)[source]
insert_GraphicRegion_at(index, value)[source]
replace_GraphicRegion_at(index, value)[source]
get_TableRegion()[source]