pdfrb 0.2.1 → 0.6.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.rubocop.yml +1 -1
- data/CHANGELOG.md +24 -0
- data/Gemfile +1 -0
- data/PROPOSAL.canvas-clip.md +92 -0
- data/PROPOSAL.canvas-draw-image-matrix.md +87 -0
- data/PROPOSAL.canvas-rich-text.md +103 -0
- data/PROPOSAL.canvas-text-lines.md +77 -0
- data/PROPOSAL.canvas-transparency.md +106 -0
- data/PROPOSAL.external-font-metrics.md +129 -0
- data/PROPOSAL.font-embedding-fontfile2.md +88 -0
- data/PROPOSAL.font-resolver-ttc.md +105 -0
- data/PROPOSAL.font-resolver.md +96 -0
- data/PROPOSAL.font-subsetting.md +98 -0
- data/PROPOSAL.gradient-shadings.md +110 -0
- data/PROPOSAL.page-mediabox-setter.md +66 -0
- data/PROPOSAL.per-glyph-width.md +91 -0
- data/PROPOSAL.stringio-require.md +53 -0
- data/PROPOSAL.struct-tree-root.md +102 -0
- data/PROPOSAL.text-measurement.md +93 -0
- data/PROPOSAL.ttf-table-parsing-fix.md +112 -0
- data/RELEASE.md +48 -0
- data/lib/pdfrb/action/base.rb +21 -0
- data/lib/pdfrb/action/types.rb +178 -0
- data/lib/pdfrb/action.rb +55 -0
- data/lib/pdfrb/annotation/base.rb +79 -0
- data/lib/pdfrb/annotation/types.rb +222 -0
- data/lib/pdfrb/annotation.rb +78 -0
- data/lib/pdfrb/appearance/generator.rb +216 -0
- data/lib/pdfrb/appearance.rb +11 -0
- data/lib/pdfrb/arlington/object_definition.rb +2 -2
- data/lib/pdfrb/arlington/predicate/evaluator.rb +1 -1
- data/lib/pdfrb/arlington/predicate/functions.rb +25 -9
- data/lib/pdfrb/arlington/predicate.rb +1 -5
- data/lib/pdfrb/cli/batch.rb +18 -0
- data/lib/pdfrb/cli/debug_info.rb +18 -0
- data/lib/pdfrb/cli/files.rb +16 -0
- data/lib/pdfrb/cli/fonts.rb +16 -0
- data/lib/pdfrb/cli/form.rb +18 -0
- data/lib/pdfrb/cli/image2pdf.rb +18 -0
- data/lib/pdfrb/cli/images.rb +34 -0
- data/lib/pdfrb/cli/info.rb +20 -0
- data/lib/pdfrb/cli/inspect.rb +18 -0
- data/lib/pdfrb/cli/merge.rb +18 -0
- data/lib/pdfrb/cli/modify.rb +18 -0
- data/lib/pdfrb/cli/optimize.rb +18 -0
- data/lib/pdfrb/cli/split.rb +21 -0
- data/lib/pdfrb/cli/watermark.rb +18 -0
- data/lib/pdfrb/cli.rb +312 -7
- data/lib/pdfrb/color/color_space.rb +259 -0
- data/lib/pdfrb/color/icc_profile.rb +90 -0
- data/lib/pdfrb/color.rb +12 -0
- data/lib/pdfrb/compare/comparator.rb +244 -0
- data/lib/pdfrb/compare/report.rb +78 -0
- data/lib/pdfrb/compare.rb +42 -0
- data/lib/pdfrb/composer.rb +161 -0
- data/lib/pdfrb/conformance/pdf_a.rb +317 -56
- data/lib/pdfrb/conformance/pdf_ua.rb +186 -29
- data/lib/pdfrb/conformance/pdf_x.rb +247 -0
- data/lib/pdfrb/conformance/rule.rb +78 -0
- data/lib/pdfrb/conformance/structure_elements.rb +174 -0
- data/lib/pdfrb/conformance/verapdf_bridge.rb +92 -0
- data/lib/pdfrb/conformance.rb +7 -3
- data/lib/pdfrb/content/canvas.rb +217 -72
- data/lib/pdfrb/content/color_space.rb +157 -0
- data/lib/pdfrb/content/hidden_text_detector.rb +167 -0
- data/lib/pdfrb/content/operator.rb +21 -1
- data/lib/pdfrb/content/operators/clipping.rb +36 -0
- data/lib/pdfrb/content/operators/graphics_state_params.rb +15 -0
- data/lib/pdfrb/content/operators.rb +21 -0
- data/lib/pdfrb/content/shading/base.rb +139 -0
- data/lib/pdfrb/content/shading.rb +17 -0
- data/lib/pdfrb/content/smart_text_extractor.rb +85 -0
- data/lib/pdfrb/content/tiling_pattern.rb +78 -0
- data/lib/pdfrb/content/transformation_matrix.rb +61 -0
- data/lib/pdfrb/content.rb +7 -26
- data/lib/pdfrb/destination/fit.rb +185 -0
- data/lib/pdfrb/destination.rb +13 -0
- data/lib/pdfrb/digital_signature/cms_handler.rb +22 -0
- data/lib/pdfrb/digital_signature/signing.rb +107 -11
- data/lib/pdfrb/digital_signature/timestamp_handler.rb +45 -0
- data/lib/pdfrb/digital_signature/verification.rb +88 -9
- data/lib/pdfrb/digital_signature/verification_result.rb +14 -0
- data/lib/pdfrb/digital_signature.rb +26 -2
- data/lib/pdfrb/document/annotations.rb +120 -3
- data/lib/pdfrb/document/associated_files.rb +104 -0
- data/lib/pdfrb/document/colors.rb +95 -0
- data/lib/pdfrb/document/destinations.rb +127 -5
- data/lib/pdfrb/document/display.rb +84 -0
- data/lib/pdfrb/document/fonts.rb +417 -45
- data/lib/pdfrb/document/form.rb +338 -0
- data/lib/pdfrb/document/form_xobject.rb +68 -0
- data/lib/pdfrb/document/graphics_state.rb +91 -0
- data/lib/pdfrb/document/images.rb +4 -4
- data/lib/pdfrb/document/info.rb +102 -0
- data/lib/pdfrb/document/layers.rb +62 -0
- data/lib/pdfrb/document/metadata.rb +12 -5
- data/lib/pdfrb/document/output_intents.rb +91 -0
- data/lib/pdfrb/document/page_labels.rb +80 -0
- data/lib/pdfrb/document/pages.rb +68 -19
- data/lib/pdfrb/document/portfolio.rb +119 -0
- data/lib/pdfrb/document/shadings.rb +159 -0
- data/lib/pdfrb/document/stamps.rb +68 -0
- data/lib/pdfrb/document/structure.rb +242 -0
- data/lib/pdfrb/document.rb +73 -4
- data/lib/pdfrb/encryption/identity.rb +13 -0
- data/lib/pdfrb/encryption/password_verification.rb +53 -8
- data/lib/pdfrb/encryption/security_handler.rb +8 -5
- data/lib/pdfrb/encryption/standard_security_handler.rb +154 -81
- data/lib/pdfrb/encryption.rb +17 -0
- data/lib/pdfrb/error.rb +2 -2
- data/lib/pdfrb/filter/brotli_decode.rb +32 -0
- data/lib/pdfrb/filter/ccitt_fax_decode.rb +12 -0
- data/lib/pdfrb/filter/crypt.rb +2 -2
- data/lib/pdfrb/filter/dct_decode.rb +18 -0
- data/lib/pdfrb/filter/flate_decode.rb +4 -18
- data/lib/pdfrb/filter/jbig2_decode.rb +12 -0
- data/lib/pdfrb/filter/jpx_decode.rb +18 -0
- data/lib/pdfrb/filter/lzw_decode.rb +3 -2
- data/lib/pdfrb/filter/png_predictor.rb +94 -0
- data/lib/pdfrb/filter.rb +26 -13
- data/lib/pdfrb/font/afm_parser.rb +50 -26
- data/lib/pdfrb/font/cmap/writer.rb +9 -0
- data/lib/pdfrb/font/encoding/win_ansi_encoding.rb +17 -0
- data/lib/pdfrb/font/encoding.rb +32 -3
- data/lib/pdfrb/font/metrics_helper.rb +121 -0
- data/lib/pdfrb/font/true_type/file.rb +10 -1
- data/lib/pdfrb/font/true_type/glyf.rb +82 -0
- data/lib/pdfrb/font/true_type/kern.rb +58 -0
- data/lib/pdfrb/font/true_type/loca.rb +42 -0
- data/lib/pdfrb/font/true_type/maxp.rb +44 -0
- data/lib/pdfrb/font/true_type/name.rb +53 -0
- data/lib/pdfrb/font/true_type/post.rb +93 -0
- data/lib/pdfrb/font/true_type/subsetter.rb +3 -5
- data/lib/pdfrb/font/true_type/wrapper.rb +102 -0
- data/lib/pdfrb/font/true_type.rb +7 -0
- data/lib/pdfrb/font.rb +2 -0
- data/lib/pdfrb/font_loader/from_configuration.rb +19 -0
- data/lib/pdfrb/font_loader/from_file.rb +20 -0
- data/lib/pdfrb/font_loader/standard14.rb +20 -0
- data/lib/pdfrb/font_loader/variant_from_name.rb +36 -0
- data/lib/pdfrb/font_loader.rb +4 -0
- data/lib/pdfrb/font_resolver.rb +138 -0
- data/lib/pdfrb/image/audit.rb +94 -0
- data/lib/pdfrb/image/downsampler.rb +124 -0
- data/lib/pdfrb/image.rb +13 -0
- data/lib/pdfrb/image_loader/jpeg.rb +39 -58
- data/lib/pdfrb/image_loader/png.rb +31 -257
- data/lib/pdfrb/layout/bidi.rb +198 -0
- data/lib/pdfrb/layout/box.rb +49 -0
- data/lib/pdfrb/layout/box_fitter.rb +54 -0
- data/lib/pdfrb/layout/column_box.rb +71 -0
- data/lib/pdfrb/layout/container_box.rb +45 -0
- data/lib/pdfrb/layout/frame.rb +67 -0
- data/lib/pdfrb/layout/image_box.rb +44 -0
- data/lib/pdfrb/layout/inline_box.rb +25 -0
- data/lib/pdfrb/layout/line.rb +55 -0
- data/lib/pdfrb/layout/list_box.rb +87 -0
- data/lib/pdfrb/layout/numeric_refinements.rb +43 -0
- data/lib/pdfrb/layout/page_style.rb +65 -0
- data/lib/pdfrb/layout/style.rb +62 -0
- data/lib/pdfrb/layout/table_box.rb +66 -0
- data/lib/pdfrb/layout/text_box.rb +38 -0
- data/lib/pdfrb/layout/text_fragment.rb +45 -0
- data/lib/pdfrb/layout/text_layouter.rb +123 -0
- data/lib/pdfrb/layout.rb +28 -0
- data/lib/pdfrb/linearization/hint_stream.rb +93 -0
- data/lib/pdfrb/linearization/writer.rb +259 -0
- data/lib/pdfrb/linearization.rb +21 -0
- data/lib/pdfrb/model/cos/dictionary.rb +12 -0
- data/lib/pdfrb/model/pdf_array.rb +2 -2
- data/lib/pdfrb/model/type/action.rb +42 -0
- data/lib/pdfrb/model/type/action_go_to_3d_view.rb +14 -0
- data/lib/pdfrb/model/type/action_go_to_dp.rb +16 -0
- data/lib/pdfrb/model/type/action_go_to_r.rb +26 -0
- data/lib/pdfrb/model/type/action_goto.rb +34 -0
- data/lib/pdfrb/model/type/action_hide.rb +26 -0
- data/lib/pdfrb/model/type/action_import_data.rb +18 -0
- data/lib/pdfrb/model/type/action_java_script.rb +18 -0
- data/lib/pdfrb/model/type/action_launch.rb +22 -0
- data/lib/pdfrb/model/type/action_movie.rb +22 -0
- data/lib/pdfrb/model/type/action_named.rb +23 -0
- data/lib/pdfrb/model/type/action_nop.rb +12 -0
- data/lib/pdfrb/model/type/action_rendition.rb +28 -0
- data/lib/pdfrb/model/type/action_reset_form.rb +22 -0
- data/lib/pdfrb/model/type/action_rich_media_execute.rb +17 -0
- data/lib/pdfrb/model/type/action_set_ocg_state.rb +32 -0
- data/lib/pdfrb/model/type/action_set_state.rb +14 -0
- data/lib/pdfrb/model/type/action_sound_action.rb +23 -0
- data/lib/pdfrb/model/type/action_submit_form.rb +64 -0
- data/lib/pdfrb/model/type/action_thread.rb +23 -0
- data/lib/pdfrb/model/type/action_trans.rb +30 -0
- data/lib/pdfrb/model/type/action_uri.rb +30 -0
- data/lib/pdfrb/model/type/af_embedded_file.rb +11 -0
- data/lib/pdfrb/model/type/af_file_specification.rb +34 -0
- data/lib/pdfrb/model/type/annotation.rb +49 -10
- data/lib/pdfrb/model/type/appearance.rb +41 -0
- data/lib/pdfrb/model/type/appearance_characteristics.rb +36 -0
- data/lib/pdfrb/model/type/appearance_generator.rb +22 -0
- data/lib/pdfrb/model/type/appearance_trap_net.rb +84 -0
- data/lib/pdfrb/model/type/border_effect.rb +25 -0
- data/lib/pdfrb/model/type/border_styling.rb +38 -0
- data/lib/pdfrb/model/type/box_color_info.rb +21 -0
- data/lib/pdfrb/model/type/box_style.rb +19 -0
- data/lib/pdfrb/model/type/button.rb +17 -0
- data/lib/pdfrb/model/type/cal_gray.rb +17 -0
- data/lib/pdfrb/model/type/cal_rgb.rb +22 -0
- data/lib/pdfrb/model/type/caret_annotation.rb +21 -0
- data/lib/pdfrb/model/type/catalog.rb +99 -16
- data/lib/pdfrb/model/type/choice.rb +21 -0
- data/lib/pdfrb/model/type/cid_font.rb +52 -1
- data/lib/pdfrb/model/type/cid_font_descriptor_metrics.rb +28 -0
- data/lib/pdfrb/model/type/cid_system_info.rb +28 -0
- data/lib/pdfrb/model/type/circle_annotation.rb +20 -0
- data/lib/pdfrb/model/type/collection.rb +27 -0
- data/lib/pdfrb/model/type/collection_field.rb +24 -0
- data/lib/pdfrb/model/type/collection_item.rb +19 -0
- data/lib/pdfrb/model/type/collection_schema.rb +25 -0
- data/lib/pdfrb/model/type/collection_sort.rb +13 -0
- data/lib/pdfrb/model/type/crypt_filter.rb +58 -0
- data/lib/pdfrb/model/type/device_n.rb +37 -0
- data/lib/pdfrb/model/type/device_n_mixing_hints.rb +17 -0
- data/lib/pdfrb/model/type/device_n_process.rb +13 -0
- data/lib/pdfrb/model/type/doc_mdp_transform_parameters.rb +21 -0
- data/lib/pdfrb/model/type/document_security_store.rb +55 -0
- data/lib/pdfrb/model/type/embedded_file.rb +19 -0
- data/lib/pdfrb/model/type/embedded_file_parameter.rb +48 -0
- data/lib/pdfrb/model/type/encryption_public_key.rb +38 -0
- data/lib/pdfrb/model/type/encryption_standard.rb +68 -0
- data/lib/pdfrb/model/type/field_mdp_transform_parameters.rb +26 -0
- data/lib/pdfrb/model/type/file_attachment_annotation.rb +29 -0
- data/lib/pdfrb/model/type/file_spec_ef.rb +22 -0
- data/lib/pdfrb/model/type/file_spec_rf.rb +21 -0
- data/lib/pdfrb/model/type/file_specification.rb +43 -0
- data/lib/pdfrb/model/type/file_trailer.rb +54 -0
- data/lib/pdfrb/model/type/font.rb +73 -2
- data/lib/pdfrb/model/type/font_cid_type0.rb +17 -0
- data/lib/pdfrb/model/type/font_cid_type2.rb +17 -0
- data/lib/pdfrb/model/type/font_descriptor.rb +47 -0
- data/lib/pdfrb/model/type/font_descriptor_cid_type0.rb +15 -0
- data/lib/pdfrb/model/type/font_descriptor_cid_type2.rb +15 -0
- data/lib/pdfrb/model/type/font_encoding.rb +47 -0
- data/lib/pdfrb/model/type/font_file.rb +28 -0
- data/lib/pdfrb/model/type/font_file2.rb +32 -0
- data/lib/pdfrb/model/type/font_file3.rb +23 -0
- data/lib/pdfrb/model/type/font_multiple_master.rb +60 -0
- data/lib/pdfrb/model/type/font_true_type.rb +1 -1
- data/lib/pdfrb/model/type/font_type0.rb +1 -1
- data/lib/pdfrb/model/type/font_type1.rb +1 -1
- data/lib/pdfrb/model/type/font_type3.rb +1 -1
- data/lib/pdfrb/model/type/form_field.rb +73 -0
- data/lib/pdfrb/model/type/free_text_annotation.rb +37 -0
- data/lib/pdfrb/model/type/function.rb +42 -0
- data/lib/pdfrb/model/type/function_exponential.rb +31 -0
- data/lib/pdfrb/model/type/function_postscript.rb +25 -0
- data/lib/pdfrb/model/type/function_sampled.rb +55 -0
- data/lib/pdfrb/model/type/function_stitching.rb +33 -0
- data/lib/pdfrb/model/type/generic_appearance.rb +40 -0
- data/lib/pdfrb/model/type/graphics_state_parameter.rb +69 -0
- data/lib/pdfrb/model/type/halftone.rb +21 -0
- data/lib/pdfrb/model/type/halftone_type1.rb +17 -0
- data/lib/pdfrb/model/type/halftone_type10.rb +16 -0
- data/lib/pdfrb/model/type/halftone_type16.rb +11 -0
- data/lib/pdfrb/model/type/halftone_type5.rb +24 -0
- data/lib/pdfrb/model/type/halftone_type6.rb +16 -0
- data/lib/pdfrb/model/type/highlight_annotation.rb +11 -0
- data/lib/pdfrb/model/type/icc_based_color_space.rb +24 -0
- data/lib/pdfrb/model/type/icon_fit.rb +31 -0
- data/lib/pdfrb/model/type/indexed.rb +32 -0
- data/lib/pdfrb/model/type/info.rb +44 -0
- data/lib/pdfrb/model/type/ink_annotation.rb +29 -0
- data/lib/pdfrb/model/type/interactive_form.rb +36 -0
- data/lib/pdfrb/model/type/interior_color.rb +12 -0
- data/lib/pdfrb/model/type/jbig2_globals.rb +15 -0
- data/lib/pdfrb/model/type/lab.rb +27 -0
- data/lib/pdfrb/model/type/line_annotation.rb +44 -0
- data/lib/pdfrb/model/type/line_ending_styling.rb +39 -0
- data/lib/pdfrb/model/type/link_annotation.rb +41 -0
- data/lib/pdfrb/model/type/link_appearance.rb +9 -0
- data/lib/pdfrb/model/type/mark_information.rb +23 -0
- data/lib/pdfrb/model/type/marked_content_reference.rb +24 -0
- data/lib/pdfrb/model/type/markup_annotation.rb +36 -0
- data/lib/pdfrb/model/type/mdp_dict.rb +28 -0
- data/lib/pdfrb/model/type/measure.rb +39 -0
- data/lib/pdfrb/model/type/media_clip.rb +28 -0
- data/lib/pdfrb/model/type/media_offset.rb +106 -0
- data/lib/pdfrb/model/type/metadata.rb +27 -3
- data/lib/pdfrb/model/type/misc_helpers.rb +75 -0
- data/lib/pdfrb/model/type/movie.rb +28 -0
- data/lib/pdfrb/model/type/names.rb +51 -0
- data/lib/pdfrb/model/type/namespace.rb +27 -0
- data/lib/pdfrb/model/type/object_reference.rb +31 -0
- data/lib/pdfrb/model/type/object_stream.rb +38 -0
- data/lib/pdfrb/model/type/opt_content_ext.rb +94 -0
- data/lib/pdfrb/model/type/opt_content_page_element.rb +18 -0
- data/lib/pdfrb/model/type/optional_content_config.rb +56 -0
- data/lib/pdfrb/model/type/optional_content_group.rb +35 -10
- data/lib/pdfrb/model/type/optional_content_membership.rb +36 -2
- data/lib/pdfrb/model/type/optional_content_properties.rb +16 -1
- data/lib/pdfrb/model/type/outline.rb +40 -6
- data/lib/pdfrb/model/type/outline_item.rb +45 -0
- data/lib/pdfrb/model/type/output_intent.rb +30 -0
- data/lib/pdfrb/model/type/page.rb +127 -0
- data/lib/pdfrb/model/type/page_label.rb +68 -0
- data/lib/pdfrb/model/type/page_tree_node.rb +51 -16
- data/lib/pdfrb/model/type/page_tree_node_root.rb +15 -0
- data/lib/pdfrb/model/type/pattern.rb +16 -0
- data/lib/pdfrb/model/type/pattern_shading.rb +25 -0
- data/lib/pdfrb/model/type/pattern_tiling.rb +25 -0
- data/lib/pdfrb/model/type/polygon_annotation.rb +29 -0
- data/lib/pdfrb/model/type/polygon_polyline.rb +14 -0
- data/lib/pdfrb/model/type/polyline_annotation.rb +29 -0
- data/lib/pdfrb/model/type/popup_annotation.rb +20 -0
- data/lib/pdfrb/model/type/printer_mark_annotation.rb +13 -0
- data/lib/pdfrb/model/type/redact_annotation.rb +28 -0
- data/lib/pdfrb/model/type/rendition.rb +31 -0
- data/lib/pdfrb/model/type/resources.rb +59 -14
- data/lib/pdfrb/model/type/rich_media_activation.rb +24 -0
- data/lib/pdfrb/model/type/rich_media_animation.rb +25 -0
- data/lib/pdfrb/model/type/rich_media_annotation.rb +18 -0
- data/lib/pdfrb/model/type/rich_media_command.rb +19 -0
- data/lib/pdfrb/model/type/rich_media_configuration.rb +32 -0
- data/lib/pdfrb/model/type/rich_media_content.rb +28 -0
- data/lib/pdfrb/model/type/rich_media_cue_point.rb +18 -0
- data/lib/pdfrb/model/type/rich_media_deactivation.rb +17 -0
- data/lib/pdfrb/model/type/rich_media_instance.rb +33 -0
- data/lib/pdfrb/model/type/rich_media_presentation.rb +29 -0
- data/lib/pdfrb/model/type/rich_media_settings.rb +33 -0
- data/lib/pdfrb/model/type/rich_media_window.rb +20 -0
- data/lib/pdfrb/model/type/screen_annotation.rb +19 -0
- data/lib/pdfrb/model/type/separation.rb +25 -0
- data/lib/pdfrb/model/type/sig_field_lock.rb +25 -0
- data/lib/pdfrb/model/type/sig_field_seed_value.rb +25 -0
- data/lib/pdfrb/model/type/signature.rb +65 -0
- data/lib/pdfrb/model/type/signature_build.rb +86 -0
- data/lib/pdfrb/model/type/signature_field.rb +17 -0
- data/lib/pdfrb/model/type/software_identifier.rb +19 -0
- data/lib/pdfrb/model/type/sound.rb +38 -0
- data/lib/pdfrb/model/type/sound_annotation.rb +21 -0
- data/lib/pdfrb/model/type/square_annotation.rb +24 -0
- data/lib/pdfrb/model/type/square_circle.rb +13 -0
- data/lib/pdfrb/model/type/squiggly_annotation.rb +11 -0
- data/lib/pdfrb/model/type/stamp_annotation.rb +19 -0
- data/lib/pdfrb/model/type/strikeout_annotation.rb +11 -0
- data/lib/pdfrb/model/type/struct_elem.rb +75 -0
- data/lib/pdfrb/model/type/struct_tree_root.rb +34 -0
- data/lib/pdfrb/model/type/structure_attributes.rb +44 -0
- data/lib/pdfrb/model/type/structure_element_kid.rb +33 -0
- data/lib/pdfrb/model/type/text_annotation.rb +25 -0
- data/lib/pdfrb/model/type/text_appearance.rb +9 -0
- data/lib/pdfrb/model/type/text_field.rb +21 -0
- data/lib/pdfrb/model/type/text_markup_annotation.rb +30 -0
- data/lib/pdfrb/model/type/three_d_activation.rb +32 -0
- data/lib/pdfrb/model/type/three_d_animation_style.rb +24 -0
- data/lib/pdfrb/model/type/three_d_background.rb +28 -0
- data/lib/pdfrb/model/type/three_d_cross_section.rb +25 -0
- data/lib/pdfrb/model/type/three_d_lighting_scheme.rb +26 -0
- data/lib/pdfrb/model/type/three_d_measure.rb +20 -0
- data/lib/pdfrb/model/type/three_d_measure_3dc.rb +23 -0
- data/lib/pdfrb/model/type/three_d_measure_ad3.rb +14 -0
- data/lib/pdfrb/model/type/three_d_measure_ld3.rb +14 -0
- data/lib/pdfrb/model/type/three_d_measure_pd3.rb +20 -0
- data/lib/pdfrb/model/type/three_d_measure_rd3.rb +14 -0
- data/lib/pdfrb/model/type/three_d_node.rb +37 -0
- data/lib/pdfrb/model/type/three_d_reference.rb +21 -0
- data/lib/pdfrb/model/type/three_d_render_mode.rb +34 -0
- data/lib/pdfrb/model/type/three_d_stream.rb +48 -0
- data/lib/pdfrb/model/type/three_d_units.rb +18 -0
- data/lib/pdfrb/model/type/three_d_view.rb +40 -0
- data/lib/pdfrb/model/type/to_unicode_cmap_stream.rb +23 -0
- data/lib/pdfrb/model/type/transition.rb +68 -0
- data/lib/pdfrb/model/type/underline_annotation.rb +11 -0
- data/lib/pdfrb/model/type/ur_transform_parameters.rb +33 -0
- data/lib/pdfrb/model/type/uri_dict.rb +18 -0
- data/lib/pdfrb/model/type/url_alias.rb +19 -0
- data/lib/pdfrb/model/type/variable_text_field.rb +47 -0
- data/lib/pdfrb/model/type/viewer_preferences.rb +42 -0
- data/lib/pdfrb/model/type/watermark_annotation.rb +13 -0
- data/lib/pdfrb/model/type/widget_annotation.rb +48 -0
- data/lib/pdfrb/model/type/widget_appearance.rb +9 -0
- data/lib/pdfrb/model/type/xobject_form.rb +41 -0
- data/lib/pdfrb/model/type/xobject_image.rb +56 -0
- data/lib/pdfrb/model/type/xref_stream.rb +37 -0
- data/lib/pdfrb/model/type.rb +286 -6
- data/lib/pdfrb/serializer.rb +2 -2
- data/lib/pdfrb/source/tokenizer.rb +0 -2
- data/lib/pdfrb/task/benchmark.rb +83 -0
- data/lib/pdfrb/task/extract_text.rb +1 -1
- data/lib/pdfrb/task/generate_corpus.rb +130 -0
- data/lib/pdfrb/task/memory_profile.rb +84 -0
- data/lib/pdfrb/task/optimize.rb +97 -7
- data/lib/pdfrb/task.rb +3 -3
- data/lib/pdfrb/test_utils.rb +112 -0
- data/lib/pdfrb/validator.rb +82 -0
- data/lib/pdfrb/version.rb +1 -1
- data/lib/pdfrb/writer.rb +117 -27
- data/lib/pdfrb/xmp/packet.rb +122 -0
- data/lib/pdfrb/xmp/schemas.rb +96 -0
- data/lib/pdfrb/xmp.rb +44 -0
- data/lib/pdfrb/xref_section.rb +2 -2
- data/lib/pdfrb.rb +25 -53
- data/pdfrb.gemspec +45 -0
- data/script/apply_fixes.sh +843 -0
- data/script/make_jpeg_fixture.rb +53 -0
- data/script/make_png_fixture.rb +25 -0
- metadata +312 -2
|
@@ -0,0 +1,174 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Pdfrb
|
|
4
|
+
module Conformance
|
|
5
|
+
# Per-structure-element validation rules derived from the PDF
|
|
6
|
+
# Association's "Tagged PDF Best Practice Guide: Syntax" (BPG).
|
|
7
|
+
#
|
|
8
|
+
# Each standard structure type has expected children and attributes.
|
|
9
|
+
# This module provides a registry of structure-type validators
|
|
10
|
+
# (OCP: add a validator = register, no switch edits).
|
|
11
|
+
module StructureElements
|
|
12
|
+
# Standard PDF structure types (ISO 32000-2 §14.8.4).
|
|
13
|
+
TABLE_CHILDREN = %i[TR THead TBody TFoot].freeze
|
|
14
|
+
STANDARD_TYPES = %i[
|
|
15
|
+
Document Part Art Sect Div BlockQuote Caption
|
|
16
|
+
TOC TOCI Index NonStruct Private
|
|
17
|
+
H H1 H2 H3 H4 H5 H6
|
|
18
|
+
P L LI Lbl LBody
|
|
19
|
+
Table TR TH TD THead TBody TFoot
|
|
20
|
+
Span Quote Note Reference BibEntry Code
|
|
21
|
+
Figure Formula Form
|
|
22
|
+
Ruby RB RT RP
|
|
23
|
+
Warichu WT WP
|
|
24
|
+
Annot
|
|
25
|
+
].freeze
|
|
26
|
+
|
|
27
|
+
# Map of structure type → expected child types (nil = any).
|
|
28
|
+
EXPECTED_CHILDREN = {
|
|
29
|
+
L: [:LI],
|
|
30
|
+
LI: [:Lbl, :LBody],
|
|
31
|
+
Table: [:THead, :TBody, :TFoot, :TR],
|
|
32
|
+
TR: [:TH, :TD],
|
|
33
|
+
Ruby: [:RB, :RT, :RP],
|
|
34
|
+
Warichu: [:WT, :WP],
|
|
35
|
+
TOC: [:TOCI],
|
|
36
|
+
}.freeze
|
|
37
|
+
|
|
38
|
+
# Map of structure type → required attributes (besides /S).
|
|
39
|
+
REQUIRED_ATTRIBUTES = {
|
|
40
|
+
Figure: [:Alt, :ActualText], # at least one required
|
|
41
|
+
Formula: [:Alt, :ActualText], # at least one required
|
|
42
|
+
}.freeze
|
|
43
|
+
|
|
44
|
+
class << self
|
|
45
|
+
def standard_types
|
|
46
|
+
STANDARD_TYPES
|
|
47
|
+
end
|
|
48
|
+
|
|
49
|
+
def expected_children(type)
|
|
50
|
+
EXPECTED_CHILDREN[type]
|
|
51
|
+
end
|
|
52
|
+
|
|
53
|
+
def required_attributes(type)
|
|
54
|
+
REQUIRED_ATTRIBUTES[type]
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
def standard?(type)
|
|
58
|
+
STANDARD_TYPES.include?(type.to_sym)
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
def validate(document)
|
|
62
|
+
violations = []
|
|
63
|
+
|
|
64
|
+
root_ref = document.catalog[:StructTreeRoot]
|
|
65
|
+
return ValidationResult.new(profile: "structure-elements", violations: []) unless root_ref
|
|
66
|
+
|
|
67
|
+
root = if root_ref.is_a?(Pdfrb::Model::Reference)
|
|
68
|
+
document.object(root_ref)
|
|
69
|
+
else
|
|
70
|
+
root_ref
|
|
71
|
+
end
|
|
72
|
+
return ValidationResult.new(profile: "structure-elements", violations: []) unless root
|
|
73
|
+
|
|
74
|
+
check_structure(document, root, violations)
|
|
75
|
+
|
|
76
|
+
ValidationResult.new(profile: "structure-elements", violations: violations)
|
|
77
|
+
end
|
|
78
|
+
|
|
79
|
+
private
|
|
80
|
+
|
|
81
|
+
# rubocop:disable Metrics/MethodLength, Metrics/AbcSize, Metrics/BlockLength
|
|
82
|
+
def check_structure(document, elem, violations, depth = 0)
|
|
83
|
+
return if depth > 20
|
|
84
|
+
|
|
85
|
+
s = elem[:S]
|
|
86
|
+
children = elem[:K]
|
|
87
|
+
|
|
88
|
+
if s && !standard?(s)
|
|
89
|
+
role_map = resolve_role_map(document, s)
|
|
90
|
+
unless role_map
|
|
91
|
+
violations << Violation.new(
|
|
92
|
+
rule_id: "ua-9",
|
|
93
|
+
message: "Non-standard structure type #{s} without role mapping",
|
|
94
|
+
object: "StructElem/#{s}",
|
|
95
|
+
severity: :error,
|
|
96
|
+
spec_clause: "ISO 14289-1 7.1"
|
|
97
|
+
)
|
|
98
|
+
end
|
|
99
|
+
end
|
|
100
|
+
|
|
101
|
+
if children
|
|
102
|
+
children = Array(children) unless children.is_a?(::Array)
|
|
103
|
+
expected = s ? expected_children(s.to_sym) : nil
|
|
104
|
+
if expected
|
|
105
|
+
children.each do |child_ref|
|
|
106
|
+
child = if child_ref.is_a?(Pdfrb::Model::Reference)
|
|
107
|
+
document.object(child_ref)
|
|
108
|
+
else
|
|
109
|
+
child_ref
|
|
110
|
+
end
|
|
111
|
+
next unless child
|
|
112
|
+
|
|
113
|
+
child_s = child[:S]
|
|
114
|
+
next unless child_s
|
|
115
|
+
|
|
116
|
+
if s == :L && child_s != :LI
|
|
117
|
+
violations << Violation.new(
|
|
118
|
+
rule_id: "ua-10",
|
|
119
|
+
message: "List has non-LI child: #{child_s}",
|
|
120
|
+
object: "StructElem/#{child_s}",
|
|
121
|
+
severity: :error,
|
|
122
|
+
spec_clause: "ISO 14289-1 7.2"
|
|
123
|
+
)
|
|
124
|
+
end
|
|
125
|
+
|
|
126
|
+
if s.to_sym == :Table && !TABLE_CHILDREN.include?(child_s.to_sym)
|
|
127
|
+
violations << Violation.new(
|
|
128
|
+
rule_id: "ua-11",
|
|
129
|
+
message: "Table has non-TR child: #{child_s}",
|
|
130
|
+
object: "StructElem/#{child_s}",
|
|
131
|
+
severity: :error,
|
|
132
|
+
spec_clause: "ISO 14289-1 7.2"
|
|
133
|
+
)
|
|
134
|
+
end
|
|
135
|
+
|
|
136
|
+
check_structure(document, child, violations, depth + 1)
|
|
137
|
+
end
|
|
138
|
+
else
|
|
139
|
+
children.each do |child_ref|
|
|
140
|
+
child = if child_ref.is_a?(Pdfrb::Model::Reference)
|
|
141
|
+
document.object(child_ref)
|
|
142
|
+
else
|
|
143
|
+
child_ref
|
|
144
|
+
end
|
|
145
|
+
next unless child
|
|
146
|
+
|
|
147
|
+
check_structure(document, child, violations, depth + 1)
|
|
148
|
+
end
|
|
149
|
+
end
|
|
150
|
+
end
|
|
151
|
+
end
|
|
152
|
+
# rubocop:enable Metrics/MethodLength, Metrics/AbcSize, Metrics/BlockLength
|
|
153
|
+
|
|
154
|
+
def resolve_role_map(document, type)
|
|
155
|
+
root_ref = document.catalog[:StructTreeRoot]
|
|
156
|
+
return nil unless root_ref
|
|
157
|
+
|
|
158
|
+
root = if root_ref.is_a?(Pdfrb::Model::Reference)
|
|
159
|
+
document.object(root_ref)
|
|
160
|
+
else
|
|
161
|
+
root_ref
|
|
162
|
+
end
|
|
163
|
+
return nil unless root
|
|
164
|
+
|
|
165
|
+
rm = root[:RoleMap]
|
|
166
|
+
return nil unless rm
|
|
167
|
+
|
|
168
|
+
rm = document.object(rm) if rm.is_a?(Pdfrb::Model::Reference)
|
|
169
|
+
rm&.value&.key?(type.to_sym)
|
|
170
|
+
end
|
|
171
|
+
end
|
|
172
|
+
end
|
|
173
|
+
end
|
|
174
|
+
end
|
|
@@ -0,0 +1,92 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "open3"
|
|
4
|
+
require "tempfile"
|
|
5
|
+
require "stringio"
|
|
6
|
+
|
|
7
|
+
module Pdfrb
|
|
8
|
+
module Conformance
|
|
9
|
+
# Bridge to veraPDF for authoritative PDF/A validation. veraPDF
|
|
10
|
+
# is the official open-source PDF/A conformance checker.
|
|
11
|
+
#
|
|
12
|
+
# If veraPDF is not installed, all methods return a Result with
|
|
13
|
+
# `available: false`. Install veraPDF from https://verapdf.org/.
|
|
14
|
+
#
|
|
15
|
+
# Usage:
|
|
16
|
+
# result = Pdfrb::Conformance::VeraPdfBridge.validate(pdf_bytes, profile: "1b")
|
|
17
|
+
# result.passed?
|
|
18
|
+
class VeraPdfBridge
|
|
19
|
+
Result = Struct.new(:available, :passed, :violations, :raw_output,
|
|
20
|
+
keyword_init: true) do
|
|
21
|
+
def passed?
|
|
22
|
+
available && self[:passed]
|
|
23
|
+
end
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
Violation = Struct.new(:rule_id, :message, :spec_clause, keyword_init: true)
|
|
27
|
+
|
|
28
|
+
class << self
|
|
29
|
+
def available?
|
|
30
|
+
_, status = Open3.capture2e("verapdf --version")
|
|
31
|
+
status.success?
|
|
32
|
+
rescue StandardError
|
|
33
|
+
false
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
def validate(pdf_bytes, profile: "2b")
|
|
37
|
+
return Result.new(available: false) unless available?
|
|
38
|
+
|
|
39
|
+
Tempfile.create(["pdfrb", ".pdf"], binmode: true) do |file|
|
|
40
|
+
file.write(pdf_bytes)
|
|
41
|
+
file.flush
|
|
42
|
+
|
|
43
|
+
output, status = Open3.capture2e("verapdf --profile #{profile} --format json #{file.path}")
|
|
44
|
+
|
|
45
|
+
Result.new(
|
|
46
|
+
available: true,
|
|
47
|
+
passed: status.success?,
|
|
48
|
+
violations: parse_violations(output),
|
|
49
|
+
raw_output: output
|
|
50
|
+
)
|
|
51
|
+
end
|
|
52
|
+
rescue StandardError => e
|
|
53
|
+
Result.new(available: false, raw_output: e.message)
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
def parse_violations(json_output)
|
|
57
|
+
return [] unless json_output && !json_output.empty?
|
|
58
|
+
|
|
59
|
+
require "json"
|
|
60
|
+
data = safe_parse(json_output)
|
|
61
|
+
return [] unless data
|
|
62
|
+
|
|
63
|
+
assertions = dig_string_path(data, ["report", "jobs", 0, "validationResult", "details", "assertions"])
|
|
64
|
+
return [] unless assertions
|
|
65
|
+
|
|
66
|
+
assertions.map do |a|
|
|
67
|
+
Violation.new(
|
|
68
|
+
rule_id: a["ruleId"],
|
|
69
|
+
message: a["message"],
|
|
70
|
+
spec_clause: a["clause"]
|
|
71
|
+
)
|
|
72
|
+
end
|
|
73
|
+
end
|
|
74
|
+
|
|
75
|
+
def dig_string_path(hash, path)
|
|
76
|
+
path.reduce(hash) do |current, key|
|
|
77
|
+
case current
|
|
78
|
+
when ::Hash then current[key]
|
|
79
|
+
when ::Array then key.is_a?(::Integer) ? current[key] : nil
|
|
80
|
+
end
|
|
81
|
+
end
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
def safe_parse(json_output)
|
|
85
|
+
JSON.parse(json_output)
|
|
86
|
+
rescue StandardError
|
|
87
|
+
nil
|
|
88
|
+
end
|
|
89
|
+
end
|
|
90
|
+
end
|
|
91
|
+
end
|
|
92
|
+
end
|
data/lib/pdfrb/conformance.rb
CHANGED
|
@@ -1,11 +1,15 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
3
|
module Pdfrb
|
|
4
|
-
# PDF/A conformance checks (ISO 19005). Subset of constraints on
|
|
5
|
-
# top of ISO 32000-2: no JavaScript, no encryption (A-1), embedded
|
|
6
|
-
# fonts required, XMP metadata required, etc.
|
|
7
4
|
module Conformance
|
|
5
|
+
autoload :Rule, "pdfrb/conformance/rule"
|
|
6
|
+
autoload :RuleSet, "pdfrb/conformance/rule"
|
|
7
|
+
autoload :Violation, "pdfrb/conformance/rule"
|
|
8
|
+
autoload :ValidationResult, "pdfrb/conformance/rule"
|
|
8
9
|
autoload :PdfA, "pdfrb/conformance/pdf_a"
|
|
9
10
|
autoload :PdfUA, "pdfrb/conformance/pdf_ua"
|
|
11
|
+
autoload :PdfX, "pdfrb/conformance/pdf_x"
|
|
12
|
+
autoload :StructureElements, "pdfrb/conformance/structure_elements"
|
|
13
|
+
autoload :VeraPdfBridge, "pdfrb/conformance/verapdf_bridge"
|
|
10
14
|
end
|
|
11
15
|
end
|