acrofill 0.1.2 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8192b1e65d4be56876296608eecae9371866700b8a2016d6bbedad79062fca33
-  data.tar.gz: 750c2b6ccd33d9e335933c6f5e5f906f0ca8adb0f5aa07e98a4eb6019104c0f9
+  metadata.gz: c3fd7c0e555d7ae744ba74b2c4bde970f938db256eb22d364584d1923650fa8a
+  data.tar.gz: 2f1f9205e4562e4dd6b483fa2a13a3855cb167c6c3d9b18b92871b3af87a2589
 SHA512:
-  metadata.gz: c081d29edbd239103797267d4f47cf2ed18ef3fa46026acae8ffc03b8d27e1b13e9477bba89c7646a554774059905bd833cd7d5df41717d95eb90ab72286d0f6
-  data.tar.gz: a0b575761f075a4fc8f7690b85ec7addee099fcf5ef29ff5f1201e72ee47fd873398645c2dd51af07476073f3cb85f8cbc7570b46af158900372201c60841098
+  metadata.gz: c6abbdd9dd06f176b5d916fc8e6a5ab6345b827fb177eb4a8d1844dd6d0d544ab1dc1eca085f33fbd032c05e56bd84506acdc582c610c35ad9fe1335a168f0e1
+  data.tar.gz: fc8550ec29027ee7b8d8023ca441a2aeb39efbc213493852db77bd28a1729d95dfee2dc5b123c31479be74696783c357ba52f1c33a11eb09993bab93ab796e82

data/CHANGELOG.md

@@ -7,6 +7,39 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.0] - 2026-07-27
+
+### Fixed
+
+- Pages whose `/Type` entry is missing are no longer skipped: flattening
+  such a document silently produced an unflattened file.
+- A widget whose appearance cannot be regenerated (degenerate `/Rect`)
+  now has its `/AP` dropped instead of keeping the appearance of the
+  *previous* value while `/V` already holds the new one.
+- A page `/Resources` or `/Resources /XObject` that is not a dictionary
+  no longer raises `TypeError` while flattening, and a `/Root` that is
+  missing or not a dictionary raises `Acrofill::Error` instead of
+  `NoMethodError`.
+- Filling a field whose fully-qualified name is shared by several field
+  dictionaries no longer depends on the return value of the first fill.
+
+### Changed
+
+- Text metrics now cover all standard-14 text cuts (Times bold/italic,
+  the Courier family, the oblique Helvetica cuts) over the full
+  WinAnsiEncoding range instead of ASCII-only Helvetica/Courier/
+  Times-Roman, so accented characters and bold or serif faces are
+  measured rather than approximated. Widths are WinAnsi-correct: `'`
+  measured 222 (StandardEncoding `quoteright`) where appearances
+  actually emit `quotesingle`.
+- Unknown `/BaseFont` names (`ArialMT`, `TimesNewRomanPS-BoldMT`, subset
+  faces) are classified by family and weight instead of all falling back
+  to Helvetica.
+- One fallback Helvetica font object is now shared by every generated
+  appearance; a 50-field form previously wrote 50 identical font
+  dictionaries.
+- Flattening moved out of `Form` into its own `Acrofill::Flattener`.
+
 ## [0.1.2] - 2026-07-24
 
 ### Added
@@ -54,7 +87,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `PdfForms`-compatible entry points (`Acrofill.new`, `fill_form`, `fields`,
   `field_names`).
 
-[Unreleased]: https://github.com/stiig/acrofill/compare/v0.1.2...HEAD
+[Unreleased]: https://github.com/stiig/acrofill/compare/v0.2.0...HEAD
+[0.2.0]: https://github.com/stiig/acrofill/compare/v0.1.2...v0.2.0
 [0.1.2]: https://github.com/stiig/acrofill/compare/v0.1.1...v0.1.2
 [0.1.1]: https://github.com/stiig/acrofill/compare/v0.1.0...v0.1.1
 [0.1.0]: https://github.com/stiig/acrofill/releases/tag/v0.1.0

data/README.md

@@ -147,9 +147,10 @@ corruption or code execution. Specifically it defends against:
   name and only well-formed colour operators (`g`/`rg`/`k`) are copied
   into generated appearances. Field **values** are always written as
   escaped literals / hex strings, never as operators.
-- **Malformed scalars** — non-finite reals, deeply nested arrays, and
-  mistyped dictionaries are clamped or rejected rather than crashing the
-  writer.
+- **Malformed scalars and mistyped structure** — non-finite reals, deeply
+  nested arrays, a `/Resources` that is not a dictionary, a `/Root` that
+  points nowhere: each is clamped, replaced or rejected rather than
+  raising a `TypeError`/`NoMethodError` out of the middle of a fill.
 - **Encrypted / unparseable input** — rejected up front; every failure
   at the parse boundary surfaces as `Acrofill::Error` (including lazy
   per-object parse errors and parser stack overflow on pathologically
@@ -162,8 +163,11 @@ Supported:
 - Text fields (`/Tx`) — hierarchical names (`parent.kid`), inherited
   `/DA`, alignment via `/Q` (left/center/right), auto font size (`0 Tf`),
   shrink-to-fit for overflowing values, multiline fields (`/Ff` bit 13)
-  with word wrapping, standard-14 width metrics
-  (Helvetica/Courier/Times).
+  with word wrapping, and WinAnsi width metrics for all standard-14 text
+  cuts (Helvetica/Times/Courier, regular through bold-italic). A
+  template's own `/BaseFont` — `ArialMT`, `TimesNewRomanPS-BoldMT`, an
+  embedded subset — is classified by family and weight rather than all
+  measured as Helvetica.
 - Checkboxes and radio groups (`/Btn`) — state selection via `/V`+`/AS`
   using the template's own appearance states.
 - Choice fields (`/Ch`) — value set and rendered like text.

data/lib/acrofill/appearance.rb

@@ -26,22 +26,22 @@ module Acrofill
       return nil if width <= 0 || height <= 0
 
       font_name, size, color_ops = parse_da(field_node)
-      base_font = base_font_for(font_name)
+      widths = Metrics.widths_for(base_font_for(font_name))
       align = alignment(field_node)
 
       body =
         if multiline
           size = 12.0 if size <= 0
           size = size.clamp(2.0, 144.0)
-          multiline_body(value, base_font, size, width, height, align)
+          multiline_body(value, widths, size, width, height, align)
         else
           text = printable_text(value)
           size = [height * 0.66, 12.0].min if size.zero?
-          size = shrink_to_fit(text, base_font, size, width)
+          size = shrink_to_fit(text, widths, size, width)
           # Vertically center the ascent box, matching pdftk's baseline
           # placement exactly: ty = (h - ascent*size) / 2.
           ty = [(height - (size * ASCENT)) / 2.0, size * DESCENT].max
-          "#{fmt(line_x(text, base_font, size, width, align))} #{fmt(ty)} Td\n" \
+          "#{fmt(line_x(text, widths, size, width, align))} #{fmt(ty)} Td\n" \
             "(#{escape_literal(text)}) Tj\n"
         end
 
@@ -73,8 +73,8 @@ module Acrofill
       align.is_a?(Integer) ? align : 0
     end
 
-    def line_x(text, base_font, size, width, align)
-      text_width = Metrics.string_width(text, base_font, size)
+    def line_x(text, widths, size, width, align)
+      text_width = Metrics.string_width(text, widths, size)
       case align
       when 1 then [(width - text_width) / 2.0, PADDING].max
       when 2 then [width - PADDING - text_width, PADDING].max
@@ -84,10 +84,10 @@ module Acrofill
 
     # Greedy word wrap, top-down, honouring explicit line breaks. Lines
     # that would fall below the box are clipped by the BBox.
-    def multiline_body(value, base_font, size, width, height, align)
+    def multiline_body(value, widths, size, width, height, align)
       max_width = width - (2 * PADDING)
       lines = value.to_s.split(/\r\n|[\r\n]/).flat_map do |paragraph|
-        wrap_line(printable_text(paragraph), base_font, size, max_width)
+        wrap_line(printable_text(paragraph), widths, size, max_width)
       end
 
       leading = size * 1.15
@@ -95,7 +95,7 @@ module Acrofill
       body = "#{fmt(leading)} TL\n"
       previous_x = 0.0
       lines.each_with_index do |line, index|
-        x = line_x(line, base_font, size, width, align)
+        x = line_x(line, widths, size, width, align)
         body << "#{fmt(x - previous_x)} #{index.zero? ? fmt(first_y) : '0'} Td\n"
         body << "(#{escape_literal(line)}) Tj\nT*\n"
         previous_x = x
@@ -105,21 +105,21 @@ module Acrofill
 
     # Greedy wrap. Line and space widths are accumulated incrementally so
     # the cost is O(total characters), not O(words * line-length).
-    def wrap_line(text, base_font, size, max_width)
-      space = Metrics.string_width(' ', base_font, size)
+    def wrap_line(text, widths, size, max_width)
+      space = Metrics.string_width(' ', widths, size)
       lines = ['']
-      widths = [0.0]
+      so_far = [0.0]
       text.split.each do |word|
-        word_width = Metrics.string_width(word, base_font, size)
+        word_width = Metrics.string_width(word, widths, size)
         if lines.last.empty?
           lines[-1] = word
-          widths[-1] = word_width
-        elsif widths.last + space + word_width <= max_width
+          so_far[-1] = word_width
+        elsif so_far.last + space + word_width <= max_width
           lines[-1] = "#{lines.last} #{word}"
-          widths[-1] += space + word_width
+          so_far[-1] += space + word_width
         else
           lines << word
-          widths << word_width
+          so_far << word_width
         end
       end
       lines
@@ -182,9 +182,9 @@ module Acrofill
 
     # Fixed sizes that overflow the box are scaled down so the whole value
     # stays visible (Acrobat-style best-fit; pdftk would clip instead).
-    def shrink_to_fit(text, base_font, size, width)
+    def shrink_to_fit(text, widths, size, width)
       max_width = width - (2 * PADDING)
-      text_width = Metrics.string_width(text, base_font, size)
+      text_width = Metrics.string_width(text, widths, size)
       size *= max_width / text_width if text_width > max_width && text_width.positive?
       size.clamp(2.0, 144.0)
     end
@@ -192,25 +192,30 @@ module Acrofill
     # The font resource dictionary from /AcroForm /DR /Font, or {} when the
     # template supplies a malformed (non-dictionary) /DR or /Font.
     def dr_fonts
-      dr = @doc.deref(@acroform[:DR])
-      return {} unless dr.is_a?(Hash)
-
-      fonts = @doc.deref(dr[:Font])
-      fonts.is_a?(Hash) ? fonts : {}
+      @dr_fonts ||=
+        begin
+          dr = @doc.deref(@acroform[:DR])
+          fonts = dr.is_a?(Hash) ? @doc.deref(dr[:Font]) : nil
+          fonts.is_a?(Hash) ? fonts : {}
+        end
     end
 
     def base_font_for(resource_name)
       font = @doc.deref(dr_fonts[resource_name.to_sym])
-      base = font.is_a?(Hash) ? font[:BaseFont].to_s : ''
-      base.sub(/\A[A-Z]{6}\+/, '')
+      base = font.is_a?(Hash) ? @doc.deref(font[:BaseFont]).to_s : ''
+      base.sub(/\A[A-Z]{6}\+/, '') # drop the subset prefix (ABCDEF+Arial)
     end
 
     def font_ref(resource_name)
       entry = dr_fonts[resource_name.to_sym]
-      return @doc.ref_for(entry) if entry
+      entry ? @doc.ref_for(entry) : fallback_font
+    end
 
-      # Font not present in /DR: register a plain Helvetica.
-      @doc.add(Type: :Font, Subtype: :Type1, BaseFont: :Helvetica, Encoding: :WinAnsiEncoding)
+    # Font not present in /DR: register one plain Helvetica and share it
+    # across every appearance built from this form.
+    def fallback_font
+      @fallback_font ||=
+        @doc.add(Type: :Font, Subtype: :Type1, BaseFont: :Helvetica, Encoding: :WinAnsiEncoding)
     end
 
     def printable_text(value)

data/lib/acrofill/document.rb

@@ -11,6 +11,8 @@ module Acrofill
   # materialized once via pdf-reader (which transparently handles xref
   # streams and object streams), then mutated in place before writing.
   class Document
+    PAGE_NODE_TYPES = %i[Pages Page].freeze
+
     attr_reader :objects, :trailer
 
     def initialize(path)
@@ -96,8 +98,14 @@ module Acrofill
       obj.is_a?(PDF::Reader::Reference) ? obj : add(obj)
     end
 
+    # The document catalog. The trailer may point at a missing or mistyped
+    # object, so this is a parse-boundary check too: callers get an
+    # Acrofill::Error rather than a NoMethodError on nil.
     def root
-      deref(@trailer[:Root])
+      node = deref(@trailer[:Root])
+      raise Error, 'PDF has no document catalog' unless node.is_a?(Hash)
+
+      node
     end
 
     # Depth-first, document-order walk over the /Pages tree. Iterative with
@@ -118,7 +126,7 @@ module Acrofill
           seen[node.id] = true
         end
 
-        case dict[:Type]
+        case node_type(dict)
         when :Pages
           kids = deref(dict[:Kids])
           stack.concat(kids.reverse) if kids.is_a?(Array)
@@ -140,5 +148,19 @@ module Acrofill
       end
       nil
     end
+
+    private
+
+    # /Type is required on page-tree nodes but plenty of real generators omit
+    # it, and a page skipped here is a page silently not flattened. Infer it
+    # from the shape instead: a node with /Kids is an internal node, anything
+    # else reached from the page tree is a leaf.
+    def node_type(dict)
+      type = deref(dict[:Type])
+      return type if PAGE_NODE_TYPES.include?(type)
+      return nil if type.is_a?(Symbol) # something else entirely, e.g. /Font
+
+      dict.key?(:Kids) ? :Pages : :Page
+    end
   end
 end

data/lib/acrofill/flattener.rb

@@ -0,0 +1,159 @@
+# frozen_string_literal: true
+
+module Acrofill
+  # Burns widget appearances into page content and removes the interactive
+  # layer, like pdftk's `output ... flatten`. Every geometry value it reads
+  # comes from the template, so each one is validated before use.
+  class Flattener
+    HIDDEN_FLAG = 2
+
+    def initialize(doc)
+      @doc = doc
+      @stamp_counter = 0
+    end
+
+    def flatten!
+      @doc.each_page { |page| flatten_page(page) }
+      @doc.root.delete(:AcroForm)
+    end
+
+    private
+
+    # Annotation /F flags. Must be dereferenced before to_i: on a
+    # PDF::Reader::Reference, to_i returns the object *number*.
+    def annotation_flags(widget)
+      flags = @doc.deref(widget[:F])
+      flags.is_a?(Integer) ? flags : 0
+    end
+
+    def flatten_page(page)
+      annot_refs = @doc.deref(page[:Annots])
+      annot_refs = [] unless annot_refs.is_a?(Array)
+      annots = annot_refs.map { |a| [a, @doc.deref(a)] }
+      widgets, others = annots.partition { |_ref, dict| dict.is_a?(Hash) && dict[:Subtype] == :Widget }
+      return if widgets.empty?
+
+      stamps = []
+      widgets.each do |_ref, widget|
+        stamp = stamp_operations(page, widget)
+        stamps << stamp if stamp
+      end
+
+      unless stamps.empty?
+        wrap = ->(bytes) { @doc.add(StreamObject.new({}, bytes.b)) }
+        derefed = @doc.deref(page[:Contents])
+        contents = (derefed.is_a?(Array) ? derefed : [page[:Contents]]).compact
+        contents = contents.map { |stream| @doc.ref_for(stream) }
+        page[:Contents] = [wrap.call("q\n"), *contents, wrap.call("\nQ\n#{stamps.join("\n")}\n")]
+      end
+
+      remaining = others.map(&:first)
+      if remaining.empty?
+        page.delete(:Annots)
+      else
+        page[:Annots] = remaining
+      end
+    end
+
+    # Returns content-stream operations placing the widget's normal
+    # appearance onto the page, or nil when there is nothing to draw.
+    # Implements the appearance-box algorithm of PDF 32000 §12.5.5: the
+    # form's /Matrix is applied to its BBox, and the resulting extent is
+    # mapped onto the annotation rectangle.
+    def stamp_operations(page, widget)
+      return nil if annotation_flags(widget).anybits?(HIDDEN_FLAG)
+
+      ap_ref = normal_appearance(widget)
+      xobject = @doc.deref(ap_ref)
+      dict = xobject.is_a?(StreamObject) ? xobject.dict : xobject&.hash
+      return nil unless dict.is_a?(Hash)
+
+      bbox = normalize_box(@doc.deref(dict[:BBox]))
+      rect = normalize_box(@doc.deref(widget[:Rect]))
+      return nil unless bbox && rect
+
+      # Appearance streams are form XObjects, but /Type and /Subtype are
+      # sometimes omitted; /Do requires them.
+      dict[:Type] ||= :XObject
+      dict[:Subtype] ||= :Form
+
+      llx, lly, urx, ury = rect
+      bx0, by0, bx1, by1 = transformed_bbox(bbox, @doc.deref(dict[:Matrix]))
+      bw = bx1 - bx0
+      bh = by1 - by0
+      return nil if bw <= 0 || bh <= 0
+
+      sx = (urx - llx) / bw
+      sy = (ury - lly) / bh
+      name = register_xobject(page, ap_ref)
+      matrix = [sx, 0, 0, sy, llx - (bx0 * sx), lly - (by0 * sy)]
+      ops = matrix.map { |n| Serializer.format_number(n.to_f) }
+      "q #{ops.join(' ')} cm /#{name} Do Q"
+    end
+
+    # Bounding box of the (already normalized) BBox corners after the
+    # form's /Matrix (identity when absent or malformed).
+    def transformed_bbox(bbox, matrix)
+      x0, y0, x1, y1 = bbox
+      matrix = matrix.map { |m| @doc.deref(m) } if matrix.is_a?(Array)
+      return [x0, y0, x1, y1] unless matrix.is_a?(Array) && matrix.size == 6 &&
+                                     matrix.all?(Numeric)
+
+      a, b, c, d, e, f = matrix.map(&:to_f)
+      xs = []
+      ys = []
+      [[x0, y0], [x1, y0], [x0, y1], [x1, y1]].each do |x, y|
+        xs << ((a * x) + (c * y) + e)
+        ys << ((b * x) + (d * y) + f)
+      end
+      [xs.min, ys.min, xs.max, ys.max]
+    end
+
+    def normal_appearance(widget)
+      ap = @doc.deref(widget[:AP])
+      return nil unless ap.is_a?(Hash)
+
+      normal = ap[:N]
+      states = @doc.deref(normal)
+      if states.is_a?(Hash) && !states.is_a?(PDF::Reader::Stream)
+        # Pick the widget's current state; without /AS default to /Off
+        # (never an arbitrary "on" appearance for an unset checkbox).
+        state = @doc.deref(widget[:AS])
+        state = :Off unless state.is_a?(Symbol) && states.key?(state)
+        normal = states[state]
+      end
+      normal
+    end
+
+    # Derefs each element (array entries may legally be indirect objects)
+    # and returns [llx, lly, urx, ury], or nil when the box is not four
+    # numbers.
+    def normalize_box(box)
+      return nil unless box.is_a?(Array) && box.size == 4
+
+      nums = box.map { |n| @doc.deref(n) }
+      return nil unless nums.all?(Numeric)
+
+      xs = [nums[0].to_f, nums[2].to_f].sort
+      ys = [nums[1].to_f, nums[3].to_f].sort
+      [xs[0], ys[0], xs[1], ys[1]]
+    end
+
+    # A page's /Resources (and its /XObject subdictionary) are template
+    # data: anything that is not a dictionary is replaced rather than
+    # indexed, which would raise TypeError on an Array or a stream.
+    def register_xobject(page, ap_ref)
+      resources = @doc.deref(page[:Resources]) || @doc.deref(@doc.inherited_value(page, :Resources))
+      resources = resources.is_a?(Hash) ? resources.dup : {}
+      xobjects = @doc.deref(resources[:XObject])
+      xobjects = xobjects.is_a?(Hash) ? xobjects.dup : {}
+
+      @stamp_counter += 1
+      name = :"AcrofillAP#{@stamp_counter}"
+      xobjects[name] = @doc.ref_for(ap_ref)
+      resources[:XObject] = xobjects
+      page[:Resources] = resources
+      name
+    end
+  end
+end

data/lib/acrofill/form.rb

@@ -4,7 +4,6 @@ module Acrofill
   # The interactive form of a document: field lookup by fully-qualified
   # name, value filling with appearance regeneration, and flattening.
   class Form
-    HIDDEN_FLAG = 2
     MULTILINE_FLAG = 1 << 12
     PUSHBUTTON_FLAG = 1 << 16
 
@@ -46,7 +45,7 @@ module Acrofill
 
       case field_type(groups.first[:node])
       when :Btn then fill_button(groups, value)
-      when :Tx, :Ch, nil then groups.each { |group| fill_text(group, value) }.any?
+      when :Tx, :Ch, nil then fill_text_groups(groups, value)
       else false # signatures and unknown types are left untouched
       end
     end
@@ -54,8 +53,7 @@ module Acrofill
     # Stamps every visible widget appearance into its page's content and
     # removes the interactive layer, like pdftk's `output ... flatten`.
     def flatten!
-      @doc.each_page { |page| flatten_page(page) }
-      @doc.root.delete(:AcroForm)
+      Flattener.new(@doc).flatten!
     end
 
     private
@@ -76,11 +74,11 @@ module Acrofill
       flags.is_a?(Integer) ? flags : 0
     end
 
-    # Annotation /F flags. Must be dereferenced before to_i: on a
-    # PDF::Reader::Reference, to_i returns the object *number*.
-    def annotation_flags(widget)
-      flags = @doc.deref(widget[:F])
-      flags.is_a?(Integer) ? flags : 0
+    # Every group sharing this name is filled, so the walk must not
+    # short-circuit on the first one.
+    def fill_text_groups(groups, value)
+      groups.each { |group| fill_text(group, value) }
+      true
     end
 
     def fill_text(group, value)
@@ -91,11 +89,14 @@ module Acrofill
       multiline = field_flags(node).anybits?(MULTILINE_FLAG)
       group[:widgets].each do |widget|
         widget.delete(:AS)
-        if value.empty?
-          widget.delete(:AP)
+        ap_ref = @appearance.build(node, widget, value, multiline: multiline) unless value.empty?
+        # An unusable geometry yields no appearance; dropping /AP is still
+        # required, or the widget would keep rendering the *previous* value
+        # while /V already holds the new one.
+        if ap_ref
+          widget[:AP] = { N: ap_ref }
         else
-          ap_ref = @appearance.build(node, widget, value, multiline: multiline)
-          widget[:AP] = { N: ap_ref } if ap_ref
+          widget.delete(:AP)
         end
       end
       true
@@ -222,132 +223,5 @@ module Acrofill
 
       "\xFE\xFF".b + value.encode('UTF-16BE').b
     end
-
-    def flatten_page(page)
-      annot_refs = @doc.deref(page[:Annots])
-      annot_refs = [] unless annot_refs.is_a?(Array)
-      annots = annot_refs.map { |a| [a, @doc.deref(a)] }
-      widgets, others = annots.partition { |_ref, dict| dict.is_a?(Hash) && dict[:Subtype] == :Widget }
-      return if widgets.empty?
-
-      stamps = []
-      widgets.each do |_ref, widget|
-        stamp = stamp_operations(page, widget)
-        stamps << stamp if stamp
-      end
-
-      unless stamps.empty?
-        wrap = ->(bytes) { @doc.add(StreamObject.new({}, bytes.b)) }
-        derefed = @doc.deref(page[:Contents])
-        contents = (derefed.is_a?(Array) ? derefed : [page[:Contents]]).compact
-        contents = contents.map { |stream| @doc.ref_for(stream) }
-        page[:Contents] = [wrap.call("q\n"), *contents, wrap.call("\nQ\n#{stamps.join("\n")}\n")]
-      end
-
-      remaining = others.map(&:first)
-      if remaining.empty?
-        page.delete(:Annots)
-      else
-        page[:Annots] = remaining
-      end
-    end
-
-    # Returns content-stream operations placing the widget's normal
-    # appearance onto the page, or nil when there is nothing to draw.
-    # Implements the appearance-box algorithm of PDF 32000 §12.5.5: the
-    # form's /Matrix is applied to its BBox, and the resulting extent is
-    # mapped onto the annotation rectangle.
-    def stamp_operations(page, widget)
-      return nil if annotation_flags(widget).anybits?(HIDDEN_FLAG)
-
-      ap_ref = normal_appearance(widget)
-      xobject = @doc.deref(ap_ref)
-      dict = xobject.is_a?(StreamObject) ? xobject.dict : xobject&.hash
-      return nil unless dict.is_a?(Hash)
-
-      bbox = normalize_box(@doc.deref(dict[:BBox]))
-      rect = normalize_box(@doc.deref(widget[:Rect]))
-      return nil unless bbox && rect
-
-      # Appearance streams are form XObjects, but /Type and /Subtype are
-      # sometimes omitted; /Do requires them.
-      dict[:Type] ||= :XObject
-      dict[:Subtype] ||= :Form
-
-      llx, lly, urx, ury = rect
-      bx0, by0, bx1, by1 = transformed_bbox(bbox, @doc.deref(dict[:Matrix]))
-      bw = bx1 - bx0
-      bh = by1 - by0
-      return nil if bw <= 0 || bh <= 0
-
-      sx = (urx - llx) / bw
-      sy = (ury - lly) / bh
-      name = register_xobject(page, ap_ref)
-      matrix = [sx, 0, 0, sy, llx - (bx0 * sx), lly - (by0 * sy)]
-      ops = matrix.map { |n| Serializer.format_number(n.to_f) }
-      "q #{ops.join(' ')} cm /#{name} Do Q"
-    end
-
-    # Bounding box of the (already normalized) BBox corners after the
-    # form's /Matrix (identity when absent or malformed).
-    def transformed_bbox(bbox, matrix)
-      x0, y0, x1, y1 = bbox
-      matrix = matrix.map { |m| @doc.deref(m) } if matrix.is_a?(Array)
-      return [x0, y0, x1, y1] unless matrix.is_a?(Array) && matrix.size == 6 &&
-                                     matrix.all?(Numeric)
-
-      a, b, c, d, e, f = matrix.map(&:to_f)
-      xs = []
-      ys = []
-      [[x0, y0], [x1, y0], [x0, y1], [x1, y1]].each do |x, y|
-        xs << ((a * x) + (c * y) + e)
-        ys << ((b * x) + (d * y) + f)
-      end
-      [xs.min, ys.min, xs.max, ys.max]
-    end
-
-    def normal_appearance(widget)
-      ap = @doc.deref(widget[:AP])
-      return nil unless ap.is_a?(Hash)
-
-      normal = ap[:N]
-      states = @doc.deref(normal)
-      if states.is_a?(Hash) && !states.is_a?(PDF::Reader::Stream)
-        # Pick the widget's current state; without /AS default to /Off
-        # (never an arbitrary "on" appearance for an unset checkbox).
-        state = @doc.deref(widget[:AS])
-        state = :Off unless state.is_a?(Symbol) && states.key?(state)
-        normal = states[state]
-      end
-      normal
-    end
-
-    # Derefs each element (array entries may legally be indirect objects)
-    # and returns [llx, lly, urx, ury], or nil when the box is not four
-    # numbers.
-    def normalize_box(box)
-      return nil unless box.is_a?(Array) && box.size == 4
-
-      nums = box.map { |n| @doc.deref(n) }
-      return nil unless nums.all?(Numeric)
-
-      xs = [nums[0].to_f, nums[2].to_f].sort
-      ys = [nums[1].to_f, nums[3].to_f].sort
-      [xs[0], ys[0], xs[1], ys[1]]
-    end
-
-    def register_xobject(page, ap_ref)
-      resources = @doc.deref(page[:Resources]) || @doc.inherited_value(page, :Resources)
-      resources = @doc.deref(resources) || {}
-      resources = resources.dup
-      xobjects = (@doc.deref(resources[:XObject]) || {}).dup
-
-      @stamp_counter = (@stamp_counter || 0) + 1
-      name = :"AcrofillAP#{@stamp_counter}"
-      xobjects[name] = @doc.ref_for(ap_ref)
-      resources[:XObject] = xobjects
-      page[:Resources] = resources
-      name
-    end
   end
 end

data/lib/acrofill/metrics.rb

@@ -1,29 +1,172 @@
 # frozen_string_literal: true
 
-# Glyph widths (1/1000 em) for standard-14 fonts, ASCII 32..126,
-# extracted from Adobe AFM metrics. Index = char code - 32.
 module Acrofill
+  # Glyph widths (1/1000 em) for the standard-14 text fonts, indexed by
+  # WinAnsiEncoding code minus 32 (appearance streams are written as
+  # Windows-1252 bytes against a /WinAnsiEncoding font, so the byte emitted
+  # is the byte measured). Extracted from Adobe AFM metrics.
+  #
+  # Only six tables are stored: the oblique cuts of Helvetica have the same
+  # widths as the upright face, and the whole Courier family is monospaced.
+  # #widths_for maps every other BaseFont name onto them.
   module Metrics
+    DEFAULT_WIDTH = 556
+    COURIER_WIDTH = 600
+    FIRST_CODE = 32
+    LAST_CODE = 255
+    WINDOWS_1252 = Encoding::Windows_1252
+
+    # Bold/italic Times cuts, indexed by bold + 2 * italic.
+    TIMES = %w[Times-Roman Times-Bold Times-Italic Times-BoldItalic].freeze
+    # Family and weight hints for BaseFont names outside the standard 14.
+    SERIF = /times|roman|serif|georgia|garamond/
+    SANS = /sans/
+    FIXED = /courier|mono/
+    BOLD = /bold|black|heavy/
+    ITALIC = /italic|oblique/
+
     WIDTHS = {
-      'Helvetica' => [278, 278, 355, 556, 556, 889, 667, 222, 333, 333, 389, 584, 278, 333, 278, 278, 556,
-                      556, 556, 556, 556, 556, 556, 556, 556, 556, 278, 278, 584, 584, 584, 556, 1015, 667, 667, 722, 722, 667, 611, 778, 722, 278, 500, 667, 556, 833, 722, 778, 667, 778, 722, 667, 611, 722, 667, 944, 667, 667, 611, 278, 278, 278, 469, 556, 222, 556, 556, 500, 556, 556, 278, 556, 556, 222, 222, 500, 222, 833, 556, 556, 556, 556, 333, 500, 278, 556, 500, 722, 500, 500, 500, 334, 260, 334, 584],
-      'Helvetica-Bold' => [278, 333, 474, 556, 556, 889, 722, 278, 333, 333, 389, 584, 278, 333, 278, 278,
-                           556, 556, 556, 556, 556, 556, 556, 556, 556, 556, 333, 333, 584, 584, 584, 611, 975, 722, 722, 722, 722, 667, 611, 778, 722, 278, 556, 722, 611, 833, 722, 778, 667, 778, 722, 667, 611, 722, 667, 944, 667, 667, 611, 333, 278, 333, 584, 556, 278, 556, 611, 556, 611, 556, 333, 611, 611, 278, 278, 556, 278, 889, 611, 611, 611, 611, 389, 556, 333, 611, 556, 778, 556, 556, 500, 389, 280, 389, 584],
-      'Courier' => [600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600,
-                    600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600],
-      'Times-Roman' => [250, 333, 408, 500, 500, 833, 778, 333, 333, 333, 500, 564, 250, 333, 250, 278, 500,
-                        500, 500, 500, 500, 500, 500, 500, 500, 500, 278, 278, 564, 564, 564, 444, 921, 722, 667, 667, 722, 611, 556, 722, 722, 333, 389, 722, 611, 889, 722, 722, 556, 722, 667, 556, 611, 722, 722, 944, 722, 722, 611, 333, 278, 333, 469, 500, 333, 444, 500, 444, 500, 444, 333, 500, 500, 278, 278, 500, 278, 778, 500, 500, 500, 500, 333, 389, 278, 500, 500, 722, 500, 500, 444, 480, 200, 480, 541]
+      'Helvetica' => [
+        278, 278, 355, 556, 556, 889, 667, 191, 333, 333, 389, 584, 278, 333, 278, 278, 556,
+        556, 556, 556, 556, 556, 556, 556, 556, 556, 278, 278, 584, 584, 584, 556, 1015, 667,
+        667, 722, 722, 667, 611, 778, 722, 278, 500, 667, 556, 833, 722, 778, 667, 778, 722,
+        667, 611, 722, 667, 944, 667, 667, 611, 278, 278, 278, 469, 556, 333, 556, 556, 500,
+        556, 556, 278, 556, 556, 222, 222, 500, 222, 833, 556, 556, 556, 556, 333, 500, 278,
+        556, 500, 722, 500, 500, 500, 334, 260, 334, 584, nil, 556, nil, 222, 556, 333, 1000,
+        556, 556, 333, 1000, 667, 333, 1000, nil, 611, nil, nil, 222, 222, 333, 333, 350, 556,
+        1000, 333, 1000, 500, 333, 944, nil, 500, 667, 278, 333, 556, 556, 556, 556, 260, 556,
+        333, 737, 370, 556, 584, 333, 737, 333, 400, 584, 333, 333, 333, 556, 537, 278, 333,
+        333, 365, 556, 834, 834, 834, 611, 667, 667, 667, 667, 667, 667, 1000, 722, 667, 667,
+        667, 667, 278, 278, 278, 278, 722, 722, 778, 778, 778, 778, 778, 584, 778, 722, 722,
+        722, 722, 667, 667, 611, 556, 556, 556, 556, 556, 556, 889, 500, 556, 556, 556, 556,
+        278, 278, 278, 278, 556, 556, 556, 556, 556, 556, 556, 584, 611, 556, 556, 556, 556,
+        500, 556, 500
+      ].freeze,
+      'Helvetica-Bold' => [
+        278, 333, 474, 556, 556, 889, 722, 238, 333, 333, 389, 584, 278, 333, 278, 278, 556,
+        556, 556, 556, 556, 556, 556, 556, 556, 556, 333, 333, 584, 584, 584, 611, 975, 722,
+        722, 722, 722, 667, 611, 778, 722, 278, 556, 722, 611, 833, 722, 778, 667, 778, 722,
+        667, 611, 722, 667, 944, 667, 667, 611, 333, 278, 333, 584, 556, 333, 556, 611, 556,
+        611, 556, 333, 611, 611, 278, 278, 556, 278, 889, 611, 611, 611, 611, 389, 556, 333,
+        611, 556, 778, 556, 556, 500, 389, 280, 389, 584, nil, 556, nil, 278, 556, 500, 1000,
+        556, 556, 333, 1000, 667, 333, 1000, nil, 611, nil, nil, 278, 278, 500, 500, 350, 556,
+        1000, 333, 1000, 556, 333, 944, nil, 500, 667, 278, 333, 556, 556, 556, 556, 280, 556,
+        333, 737, 370, 556, 584, 333, 737, 333, 400, 584, 333, 333, 333, 611, 556, 278, 333,
+        333, 365, 556, 834, 834, 834, 611, 722, 722, 722, 722, 722, 722, 1000, 722, 667, 667,
+        667, 667, 278, 278, 278, 278, 722, 722, 778, 778, 778, 778, 778, 584, 778, 722, 722,
+        722, 722, 667, 667, 611, 556, 556, 556, 556, 556, 556, 889, 556, 556, 556, 556, 556,
+        278, 278, 278, 278, 611, 611, 611, 611, 611, 611, 611, 584, 611, 611, 611, 611, 611,
+        556, 611, 556
+      ].freeze,
+      'Times-Roman' => [
+        250, 333, 408, 500, 500, 833, 778, 180, 333, 333, 500, 564, 250, 333, 250, 278, 500,
+        500, 500, 500, 500, 500, 500, 500, 500, 500, 278, 278, 564, 564, 564, 444, 921, 722,
+        667, 667, 722, 611, 556, 722, 722, 333, 389, 722, 611, 889, 722, 722, 556, 722, 667,
+        556, 611, 722, 722, 944, 722, 722, 611, 333, 278, 333, 469, 500, 333, 444, 500, 444,
+        500, 444, 333, 500, 500, 278, 278, 500, 278, 778, 500, 500, 500, 500, 333, 389, 278,
+        500, 500, 722, 500, 500, 444, 480, 200, 480, 541, nil, 500, nil, 333, 500, 444, 1000,
+        500, 500, 333, 1000, 556, 333, 889, nil, 611, nil, nil, 333, 333, 444, 444, 350, 500,
+        1000, 333, 980, 389, 333, 722, nil, 444, 722, 250, 333, 500, 500, 500, 500, 200, 500,
+        333, 760, 276, 500, 564, 333, 760, 333, 400, 564, 300, 300, 333, 500, 453, 250, 333,
+        300, 310, 500, 750, 750, 750, 444, 722, 722, 722, 722, 722, 722, 889, 667, 611, 611,
+        611, 611, 333, 333, 333, 333, 722, 722, 722, 722, 722, 722, 722, 564, 722, 722, 722,
+        722, 722, 722, 556, 500, 444, 444, 444, 444, 444, 444, 667, 444, 444, 444, 444, 444,
+        278, 278, 278, 278, 500, 500, 500, 500, 500, 500, 500, 564, 500, 500, 500, 500, 500,
+        500, 500, 500
+      ].freeze,
+      'Times-Bold' => [
+        250, 333, 555, 500, 500, 1000, 833, 278, 333, 333, 500, 570, 250, 333, 250, 278, 500,
+        500, 500, 500, 500, 500, 500, 500, 500, 500, 333, 333, 570, 570, 570, 500, 930, 722,
+        667, 722, 722, 667, 611, 778, 778, 389, 500, 778, 667, 944, 722, 778, 611, 778, 722,
+        556, 667, 722, 722, 1000, 722, 722, 667, 333, 278, 333, 581, 500, 333, 500, 556, 444,
+        556, 444, 333, 500, 556, 278, 333, 556, 278, 833, 556, 500, 556, 556, 444, 389, 333,
+        556, 500, 722, 500, 500, 444, 394, 220, 394, 520, nil, 500, nil, 333, 500, 500, 1000,
+        500, 500, 333, 1000, 556, 333, 1000, nil, 667, nil, nil, 333, 333, 500, 500, 350, 500,
+        1000, 333, 1000, 389, 333, 722, nil, 444, 722, 250, 333, 500, 500, 500, 500, 220, 500,
+        333, 747, 300, 500, 570, 333, 747, 333, 400, 570, 300, 300, 333, 556, 540, 250, 333,
+        300, 330, 500, 750, 750, 750, 500, 722, 722, 722, 722, 722, 722, 1000, 722, 667, 667,
+        667, 667, 389, 389, 389, 389, 722, 722, 778, 778, 778, 778, 778, 570, 778, 722, 722,
+        722, 722, 722, 611, 556, 500, 500, 500, 500, 500, 500, 722, 444, 444, 444, 444, 444,
+        278, 278, 278, 278, 500, 556, 500, 500, 500, 500, 500, 570, 500, 556, 556, 556, 556,
+        500, 556, 500
+      ].freeze,
+      'Times-Italic' => [
+        250, 333, 420, 500, 500, 833, 778, 214, 333, 333, 500, 675, 250, 333, 250, 278, 500,
+        500, 500, 500, 500, 500, 500, 500, 500, 500, 333, 333, 675, 675, 675, 500, 920, 611,
+        611, 667, 722, 611, 611, 722, 722, 333, 444, 667, 556, 833, 667, 722, 611, 722, 611,
+        500, 556, 722, 611, 833, 611, 556, 556, 389, 278, 389, 422, 500, 333, 500, 500, 444,
+        500, 444, 278, 500, 500, 278, 278, 444, 278, 722, 500, 500, 500, 500, 389, 389, 278,
+        500, 444, 667, 444, 444, 389, 400, 275, 400, 541, nil, 500, nil, 333, 500, 556, 889,
+        500, 500, 333, 1000, 500, 333, 944, nil, 556, nil, nil, 333, 333, 556, 556, 350, 500,
+        889, 333, 980, 389, 333, 667, nil, 389, 556, 250, 389, 500, 500, 500, 500, 275, 500,
+        333, 760, 276, 500, 675, 333, 760, 333, 400, 675, 300, 300, 333, 500, 523, 250, 333,
+        300, 310, 500, 750, 750, 750, 500, 611, 611, 611, 611, 611, 611, 889, 667, 611, 611,
+        611, 611, 333, 333, 333, 333, 722, 667, 722, 722, 722, 722, 722, 675, 722, 722, 722,
+        722, 722, 556, 611, 500, 500, 500, 500, 500, 500, 500, 667, 444, 444, 444, 444, 444,
+        278, 278, 278, 278, 500, 500, 500, 500, 500, 500, 500, 675, 500, 500, 500, 500, 500,
+        444, 500, 444
+      ].freeze,
+      'Times-BoldItalic' => [
+        250, 389, 555, 500, 500, 833, 778, 278, 333, 333, 500, 570, 250, 333, 250, 278, 500,
+        500, 500, 500, 500, 500, 500, 500, 500, 500, 333, 333, 570, 570, 570, 500, 832, 667,
+        667, 667, 722, 667, 667, 722, 778, 389, 500, 667, 611, 889, 722, 722, 611, 722, 667,
+        556, 611, 722, 667, 889, 667, 611, 611, 333, 278, 333, 570, 500, 333, 500, 500, 444,
+        500, 444, 333, 500, 556, 278, 278, 500, 278, 778, 556, 500, 500, 500, 389, 389, 278,
+        556, 444, 667, 500, 444, 389, 348, 220, 348, 570, nil, 500, nil, 333, 500, 500, 1000,
+        500, 500, 333, 1000, 556, 333, 944, nil, 611, nil, nil, 333, 333, 500, 500, 350, 500,
+        1000, 333, 1000, 389, 333, 722, nil, 389, 611, 250, 389, 500, 500, 500, 500, 220, 500,
+        333, 747, 266, 500, 606, 333, 747, 333, 400, 570, 300, 300, 333, 576, 500, 250, 333,
+        300, 300, 500, 750, 750, 750, 500, 667, 667, 667, 667, 667, 667, 944, 667, 667, 667,
+        667, 667, 389, 389, 389, 389, 722, 722, 722, 722, 722, 722, 722, 570, 722, 722, 722,
+        722, 722, 611, 611, 500, 500, 500, 500, 500, 500, 500, 722, 444, 444, 444, 444, 444,
+        278, 278, 278, 278, 500, 556, 500, 500, 500, 500, 500, 570, 500, 556, 556, 556, 556,
+        444, 500, 444
+      ].freeze,
+      'Courier' => Array.new(LAST_CODE - FIRST_CODE + 1, COURIER_WIDTH).freeze
     }.freeze
 
-    DEFAULT_WIDTH = 556
-
-    def self.string_width(str, base_font, size)
-      table = WIDTHS[base_font] || WIDTHS['Helvetica']
-      units = str.each_char.sum do |ch|
-        code = ch.ord
-        code.between?(32, 126) ? table[code - 32] : DEFAULT_WIDTH
+    # Width of +str+ at +size+ points. +widths+ is a table from #widths_for,
+    # or a BaseFont name (resolved here, at the cost of the lookup).
+    def self.string_width(str, widths, size)
+      widths = widths_for(widths) unless widths.is_a?(Array)
+      str = to_win_ansi(str)
+      units = str.each_byte.sum do |code|
+        (code >= FIRST_CODE && widths[code - FIRST_CODE]) || DEFAULT_WIDTH
       end
       units * size / 1000.0
     end
+
+    # The width table for a BaseFont name. Standard-14 names hit the table
+    # directly; anything else (ArialMT, TimesNewRomanPS-BoldMT, a template's
+    # embedded face) is classified by family and weight, which is far closer
+    # than measuring everything as Helvetica.
+    def self.widths_for(base_font)
+      name = base_font.to_s
+      return WIDTHS[name] if WIDTHS.key?(name)
+
+      lower = name.downcase
+      return WIDTHS['Courier'] if FIXED.match?(lower)
+      return WIDTHS[TIMES[weight_index(lower)]] if serif?(lower)
+
+      WIDTHS[BOLD.match?(lower) ? 'Helvetica-Bold' : 'Helvetica']
+    end
+
+    def self.serif?(lower)
+      SERIF.match?(lower) && !SANS.match?(lower)
+    end
+
+    def self.weight_index(lower)
+      (BOLD.match?(lower) ? 1 : 0) + (ITALIC.match?(lower) ? 2 : 0)
+    end
+
+    # Appearance text is already Windows-1252; anything else is converted so
+    # that measuring and rendering agree byte for byte.
+    def self.to_win_ansi(str)
+      return str if str.encoding == WINDOWS_1252
+
+      str.encode(WINDOWS_1252, invalid: :replace, undef: :replace, replace: '?')
+    end
+
+    private_class_method :serif?, :weight_index, :to_win_ansi
   end
 end

data/lib/acrofill/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Acrofill
-  VERSION = '0.1.2'
+  VERSION = '0.2.0'
 end

data/lib/acrofill.rb

@@ -6,6 +6,7 @@ require_relative 'acrofill/metrics'
 require_relative 'acrofill/serializer'
 require_relative 'acrofill/writer'
 require_relative 'acrofill/appearance'
+require_relative 'acrofill/flattener'
 require_relative 'acrofill/form'
 require_relative 'acrofill/filler'
 require_relative 'acrofill/template'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: acrofill
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.0
 platform: ruby
 authors:
 - stiig
@@ -37,6 +37,7 @@ files:
 - lib/acrofill/appearance.rb
 - lib/acrofill/document.rb
 - lib/acrofill/filler.rb
+- lib/acrofill/flattener.rb
 - lib/acrofill/form.rb
 - lib/acrofill/metrics.rb
 - lib/acrofill/serializer.rb