pdf_oxide 0.3.76-x86_64-linux → 0.3.78-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2564172ff5edbace77d4327b8dce704fcd8ed13687bfe3e8fb196373fb276952
-  data.tar.gz: 4024b5f0a87c6e3b891e4a1bbafffee47285f0ae6d42a4eda6af3121d15406f7
+  metadata.gz: 6a8d69eaf72fd938ece65cfc89ebf4e5f0a92d9a0a240079927387fb6b163482
+  data.tar.gz: 8034a9984eb0845d66814b4bb0c6bc66e132f0ac51b663d919c254f3962ab809
 SHA512:
-  metadata.gz: 6b6907efd2d2624708e1c22bd5132c558ff6956fcdd5a3d1c9a0cdd85278d30922583ae77e788caef2c83b2dd7699549720f9c8cde10079c6b42ed9ca40acc68
-  data.tar.gz: 6a63c43a35693956573bc8f853129b04e397c5f10e5d614d0199987e0893442d70fd27df199c2fee1b337659576eed0478d347927fff3887fa06a2474ea4b33a
+  metadata.gz: 358ca5c5289dfc2087e823d0563a622dd2bc53f5369f534828b0dec4635538c6f6cd83c9aaee478aef3a32fb7c4a1d78c29fa31ca35a7b3e84a83a261f21f721
+  data.tar.gz: 51ec294585007a004cf0dcdb05ec236b489e382e55605fd758456b5cdb0c8cb6121541024148c0ec8a9b9092783dda6201a8ecf7529abcf27906acccd9621d57

data/Gemfile

@@ -6,11 +6,11 @@ gemspec
 
 group :development do
   gem 'bundler', '>= 2.0'
-  gem 'rake', '~> 13.0'
-  gem 'rspec', '~> 3.12'
-  gem 'rubocop', '~> 1.86'
-  gem 'rubocop-rspec', '~> 3.9'
+  gem 'rake', '~> 13.4'
+  gem 'rspec', '~> 3.13'
+  gem 'rubocop', '~> 1.90'
+  gem 'rubocop-rspec', '~> 3.10'
   gem 'yard', '~> 0.9'
   gem 'simplecov', '~> 0.22'
-  gem 'simplecov-lcov', '~> 0.8'
+  gem 'simplecov-lcov', '~> 0.9'
 end

data/lib/pdf_oxide/ffi/bindings.rb

@@ -92,6 +92,8 @@ module PdfOxide
 
       attach_function :pdf_document_search_page, %i[pointer string int32 bool pointer], :pointer
       attach_function :pdf_document_search_all, %i[pointer string bool pointer], :pointer
+      attach_function :pdf_document_prepare_search, %i[pointer pointer], :int32
+      attach_function :pdf_document_clear_search_index, %i[pointer pointer], :int32
       attach_function :pdf_oxide_search_result_count, [:pointer], :int32
       # Each accessor takes the results handle + index + an int32* error
       # buffer. The trailing pointer is REQUIRED — omitting it caused
@@ -1427,6 +1429,15 @@ module PdfOxide
       attach_function :pdf_oxide_crypto_set_policy, %i[pointer pointer pointer pointer pointer pointer pointer pointer], :pointer, blocking: false
       attach_function :pdf_oxide_crypto_use_fips, %i[pointer pointer pointer pointer pointer pointer pointer pointer], :pointer, blocking: false
       attach_function :pdf_oxide_element_count, %i[pointer pointer pointer pointer pointer pointer pointer pointer], :pointer, blocking: false
+      # void pdf_oxide_element_get_page_rect(const FfiElementList *elements, int32_t index,
+      #                                      float *x, float *y, float *width, float *height,
+      #                                      int32_t *error_code)
+      # Page-space extents of the span: the rect from pdf_oxide_element_get_rect with any
+      # text-matrix rotation resolved into an axis-aligned page-space hull;
+      # identical to pdf_oxide_element_get_rect for upright runs.
+      attach_function :pdf_oxide_element_get_page_rect,
+                      %i[pointer int32 pointer pointer pointer pointer pointer], :void,
+                      blocking: false
       attach_function :pdf_oxide_element_get_rect, %i[pointer pointer pointer pointer pointer pointer pointer pointer], :pointer, blocking: false
       attach_function :pdf_oxide_element_get_text, %i[pointer pointer pointer pointer pointer pointer pointer pointer], :pointer, blocking: false
       attach_function :pdf_oxide_element_get_type, %i[pointer pointer pointer pointer pointer pointer pointer pointer], :pointer, blocking: false
@@ -1643,6 +1654,13 @@ module PdfOxide
       attach_function :pdf_document_extract_text_auto, %i[pointer int32 pointer], :pointer
       attach_function :pdf_document_extract_page_auto, %i[pointer int32 string pointer], :pointer
 
+      # Structured diagnostics — malloc'd JSON array of warning objects
+      # ("[]" when there are none); free with free_string.  `category` is
+      # an open-ended snake_case token: keep it a string and tolerate
+      # tokens this binding has never seen.  The `take_` variant drains.
+      attach_function :pdf_document_structured_warnings,      %i[pointer pointer], :pointer
+      attach_function :pdf_document_take_structured_warnings, %i[pointer pointer], :pointer
+
       # Models subsystem (#519 provisioning trio).
       attach_function :pdf_oxide_prefetch_models,    %i[string pointer], :pointer
       attach_function :pdf_oxide_model_manifest,     [],                  :pointer
@@ -1740,6 +1758,17 @@ module PdfOxide
                          pointer size_t
                          pointer],
                       :pointer
+
+      # uint8_t *pdf_get_rendered_image_data(
+      #   const FfiRenderedImage *img, int32_t *data_len, int32_t *error_code)
+      # Returns the encoded image bytes (PNG or JPEG per the format the
+      # image was rendered with). Caller-owned; free with free_bytes.
+      # Overrides the auto-generated 8-pointer placeholder declared
+      # earlier in this file — that placeholder signature does not match
+      # the real 3-argument ABI and cannot be called as-is.
+      attach_function :pdf_get_rendered_image_data,
+                      %i[pointer pointer pointer],
+                      :pointer
     end
   end
 end

data/lib/pdf_oxide/pdf_document.rb

@@ -170,6 +170,32 @@ module PdfOxide
       StringMarshaller.from_c_string(ptr) || ''
     end
 
+    # This document's structured diagnostics, as a raw JSON array string
+    # (`"[]"` when there are none). Non-destructive: a later call returns
+    # the same entries plus any raised since.
+    #
+    # Left unparsed on purpose: each entry's `category` is an open-ended
+    # snake_case token and new ones ship in minor releases, so callers
+    # must tolerate tokens they do not know.
+    # @return [String] JSON array.
+    def structured_warnings
+      err = ::FFI::MemoryPointer.new(:int32)
+      ptr = Bindings.pdf_document_structured_warnings(handle, err)
+      raise_for_code(err.read_int32, 'structured_warnings')
+      StringMarshaller.from_c_string(ptr) || ''
+    end
+
+    # As {#structured_warnings}, but drains: the returned entries are
+    # removed, so a batch pipeline can read per document without the sink
+    # growing across the run.
+    # @return [String] JSON array.
+    def take_structured_warnings
+      err = ::FFI::MemoryPointer.new(:int32)
+      ptr = Bindings.pdf_document_take_structured_warnings(handle, err)
+      raise_for_code(err.read_int32, 'take_structured_warnings')
+      StringMarshaller.from_c_string(ptr) || ''
+    end
+
     # Convert one page to Markdown.
     # @param page_index [Integer]
     # @return [String] Markdown.
@@ -206,6 +232,24 @@ module PdfOxide
       parse_search_results(results)
     end
 
+    # Build the search index for every page up front, instead of the
+    # lazy per-page build {#search} otherwise does on first use.
+    def prepare_search
+      err = ::FFI::MemoryPointer.new(:int32)
+      Bindings.pdf_document_prepare_search(handle, err)
+      raise_for_code(err.read_int32, 'prepare_search')
+      nil
+    end
+
+    # Drop the cached search index, if any, freeing its memory.
+    # {#search} rebuilds it lazily on next use.
+    def clear_search_index
+      err = ::FFI::MemoryPointer.new(:int32)
+      Bindings.pdf_document_clear_search_index(handle, err)
+      raise_for_code(err.read_int32, 'clear_search_index')
+      nil
+    end
+
     # @return [Array<Hash>] AcroForm fields as an array of `{name:, value:, type:, page:}`
     #   hashes.  v0.3.55 limitation: per-field `page` is -1 because
     #   pdf_oxide's form extractor doesn't yet surface per-field page
@@ -420,26 +464,19 @@ module PdfOxide
     end
 
     def read_rendered_image_bytes(img_ptr)
-      # The cdylib renders to a "rendered image" handle.  Different
-      # accessors exist across versions; try the byte-buffer accessor
-      # first, fall back to a sensible default.
-      if Bindings.respond_to?(:pdf_oxide_rendered_image_get_bytes)
-        len_ptr = ::FFI::MemoryPointer.new(:size_t)
-        err = ::FFI::MemoryPointer.new(:int32)
-        buf = Bindings.pdf_oxide_rendered_image_get_bytes(img_ptr, len_ptr, err)
-        raise_for_code(err.read_int32, 'render_bytes')
-        return '' if buf.nil? || buf.null?
-
-        len = len_ptr.read(:size_t)
-        bytes = buf.read_string(len)
-        Bindings.free_bytes(buf) if Bindings.respond_to?(:free_bytes)
-        bytes
-      else
-        # Fall back to an empty BINARY string; render() callers see a
-        # clean error path rather than a segfault when the build is
-        # missing the rendered-image accessor.
-        ''
-      end
+      # The cdylib exposes the rendered-image byte buffer through
+      # pdf_get_rendered_image_data (data_len is *mut i32, not size_t);
+      # the caller owns the returned buffer and must free it via
+      # free_bytes.
+      len_ptr = ::FFI::MemoryPointer.new(:int32)
+      err = ::FFI::MemoryPointer.new(:int32)
+      buf = Bindings.pdf_get_rendered_image_data(img_ptr, len_ptr, err)
+      raise_for_code(err.read_int32, 'render_bytes')
+      return '' if buf.nil? || buf.null?
+
+      bytes = buf.read_string(len_ptr.read_int32)
+      Bindings.free_bytes(buf)
+      bytes
     end
 
     # Map a cdylib error code (`int32_t *err`) to the matching Ruby

data/lib/pdf_oxide/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PdfOxide
-  VERSION = '0.3.76'
+  VERSION = '0.3.78'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf_oxide
 version: !ruby/object:Gem::Version
-  version: 0.3.76
+  version: 0.3.78
 platform: x86_64-linux
 authors:
 - PDF Oxide Contributors
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-07-27 00:00:00.000000000 Z
+date: 2026-09-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ffi
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: '1.17'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: '1.17'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -44,70 +44,70 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '13.0'
+        version: '13.4'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '13.0'
+        version: '13.4'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '3.13'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '3.13'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.86'
+        version: '1.90'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.86'
+        version: '1.90'
 - !ruby/object:Gem::Dependency
   name: rubocop-rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.9'
+        version: '3.10'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.9'
+        version: '3.10'
 - !ruby/object:Gem::Dependency
   name: simplecov-lcov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '0.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '0.9'
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement