pdf-extract 0.0.1 → 0.0.2

data/lib/analysis/columns.rb

@@ -47,6 +47,9 @@ module PdfExtract
             y = body[:y] + (body[:height] * i * step)
             column_ranges << columns_at(y, body_regions)
           end
+
+          # Discard those with a coverage of 0.
+          column_ranges.reject! { |r| r.covered.zero? }
           
           # Discard those with more than x columns. They've probably hit a table.
           column_ranges.reject! { |r| r.count > pdf.settings[:max_column_count] }

data/lib/font_metrics.rb

@@ -40,6 +40,9 @@ module PdfExtract
         @bbox = font.bbox
         @glyph_width_lookup = proc { |c| font.glyph_width c }
       end
+
+      @ascent = @bbox[3] if @ascent.zero?
+      @descent = @bbox[1] if @descent.zero?
     end
 
     def glyph_width c

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 0
-  - 1
-  version: 0.0.1
+  - 2
+  version: 0.0.2
 platform: ruby
 authors: 
 - Karl Jonathan Ward
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-10-21 00:00:00 +01:00
+date: 2011-10-24 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -140,6 +140,7 @@ files:
 - bin/one-column.mask.pdf
 - bin/pdf-extract
 - bin/s002040050107_Arch_Toxicol_1994_68_8.mask.pdf
+- bin/s6.mask.pdf
 - bin/some3.mask.pdf
 - bin/some5.mask.pdf
 - bin/some6.mask.pdf