Load from filename not stream (#76)

ocropus · Sep 27, 2016 · 9b57a1e · 9b57a1e
1 parent 1333646
commit 9b57a1e
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 8 deletions.
diff --git a/hocr-combine b/hocr-combine
@@ -24,13 +24,13 @@ if len(sys.argv)<2:
     print_usage()
     sys.exit(1)
 
-doc = html.fromstring(open(sys.argv[1]).read())
+doc = html.parse(sys.argv[1])
 
 pages = doc.xpath("//*[@class='ocr_page']")
 container = pages[-1].getparent()
 
 for fname in sys.argv[2:]:
-    doc2 = html.fromstring(open(fname).read())
+    doc2 = html.parse(fname)
     pages = doc2.xpath("//*[@class='ocr_page']")
     for page in pages:
         page = doc.importNode(page,1)

diff --git a/hocr-eval b/hocr-eval
@@ -141,8 +141,8 @@ if(imgfile):
     draw=ImageDraw.Draw(im)
 
 # get pages from inputs
-truth_doc = html.fromstring(args[0])
-actual_doc = html.fromstring(args[1])
+truth_doc = html.parse(args[0])
+actual_doc = html.parse(args[1])
 
 # parse pages
 truth_pages = truth_doc.xpath("//*[@class='ocr_page']")

diff --git a/hocr-eval-geom b/hocr-eval-geom
@@ -83,8 +83,8 @@ close_match = float(close_match)
 
 ### read the hOCR files
 
-truth_doc = html.fromstring(open(args[0]).read())
-actual_doc = html.fromstring(open(args[1]).read())
+truth_doc = html.parse(args[0])
+actual_doc = html.parse(args[1])
 truth_pages = truth_doc.xpath("//*[@class='ocr_page']")
 actual_pages = actual_doc.xpath("//*[@class='ocr_page']")
 assert len(truth_pages) == len(actual_pages)

diff --git a/hocr-merge-dc b/hocr-merge-dc
@@ -33,8 +33,8 @@ if len(sys.argv)<2:
     print_usage()
     sys.exit(1)
 
-dc_doc = etree.fromstring(open(sys.argv[1]).read())
-hocr_doc = html.fromstring(open(sys.argv[2]).read())
+dc_doc = etree.parse(sys.argv[1], html.XHTMLParser())
+hocr_doc = html.parse(sys.argv[2])
 
 
 ### remove all existing META tags representing Dublin Core metadata