Add option --naming for different line name patterns

ocropus-gpageseg

@@ -78,6 +78,8 @@ group_column.add_argument('--csminaspect',type=float,default=1.1,
 
 # output parameters
 group_output = parser.add_argument_group('output parameters')
+group_output.add_argument('--naming',default=False,
+                    help='change naming of the lines with an own pattern, e.g. "--naming %%04d" for four decimal digits, default: %(default)s')
 group_output.add_argument('--gray',action='store_true',
                     help='output grayscale lines as well, default: %(default)s')
 group_output.add_argument('-p','--pad',type=int,default=3,
@@ -424,12 +426,17 @@ def process1(job):
     lines = [lines[i] for i in lsort]
     ocrolib.write_page_segmentation("%s.pseg.png"%outputdir,segmentation)
     cleaned = ocrolib.remove_noise(binary,args.noise)
+    pattern = "01%04x"
+    if (args.naming):
+       pattern = args.naming
+    pattern = "%s/"+pattern
+    print_info("with file name pattern",pattern)
     for i,l in enumerate(lines):
         binline = psegutils.extract_masked(1-cleaned,l,pad=args.pad,expand=args.expand)
-        ocrolib.write_image_binary("%s/01%04x.bin.png"%(outputdir,i+1),binline)
+        ocrolib.write_image_binary(pattern%(outputdir,i+1)+".bin.png",binline)
         if args.gray:
             grayline = psegutils.extract_masked(gray,l,pad=args.pad,expand=args.expand)
-            ocrolib.write_image_gray("%s/01%04x.nrm.png"%(outputdir,i+1),grayline)
+            ocrolib.write_image_gray(pattern%(outputdir,i+1)+".nrm.png",grayline)
     print_info("%6d  %s %4.1f %d" % (i, fname,  scale,  len(lines)))
 
 if len(args.files)==1 and os.path.isdir(args.files[0]):

ocropus-hocr

@@ -24,6 +24,8 @@ For each page like 'book/0001.bin.png', it uses the following files:
 parser.add_argument("-b","--nobreaks",action="store_true",help="don't output line breaks")
 parser.add_argument("-p","--nopars",action="store_true",help="don't output paragraphs")
 parser.add_argument("-s","--fscale",type=float,default=1.0,help="scale factor for translating xheights into font size (use 0 to disable), default: %(default)s")
+parser.add_argument('--naming',default=False,
+                    help='indicate naming of the lines with an own pattern, e.g. "--naming %%04d" for four decimal digits, default: %(default)s')
 parser.add_argument("-o","--output",default="book.html",help="output file, default: %(default)s")
 parser.add_argument('files',nargs='+')
 args = parser.parse_args()
@@ -43,13 +45,13 @@ def PN(*args):
 E("writing to",args.output)
 median_xheight = None
 dirs = [ocrolib.allsplitext(name)[0] for name in args.files]
-xhfiles = python.sum([glob.glob(d+"/??????.xheight") for d in dirs],[])
+xhfiles = python.sum([glob.glob(d+"/*.xheight") for d in dirs],[])
 if len(xhfiles)>5:
     xheights = [float(ocrolib.read_text(f)) for f in xhfiles]
     if len(xheights)>0:
         median_xheight = median(xheights)
 else:    
-    lfiles = python.sum([glob.glob(d+"/??????.bin.png") for d in dirs],[])
+    lfiles = python.sum([glob.glob(d+"/*.bin.png") for d in dirs],[])
     pyrandom.shuffle(lfiles)
     if len(lfiles)>0:
         median_xheight = 0.5*median([imread(f).shape[0] for f in lfiles[:100]])
@@ -106,8 +108,12 @@ for arg in args.files:
             last_coords = (x0,y0)
 
             # get the text for the line itself
-
-            lbase = "%s/%06x"%(base,id)
+            pattern = "01%04x"
+            if (args.naming):
+               pattern = args.naming
+            pattern = "%s/"+pattern
+            id=id-0x010000
+            lbase = pattern%(base,id)
 
             if not os.path.exists(lbase+".txt"):
                 E("note: line %s produced no output (it may not have contained text)"%(lbase+".bin.png"))

ocropus-visualize-results

@@ -46,7 +46,7 @@ def genpage(d):
         os.chdir(d)
         with open("index.html","w") as stream:
             stream.write("<h1>%s</h1>\n"%d)
-            images = sorted(glob.glob("??????.bin.png"))
+            images = sorted(glob.glob("*.bin.png"))
             for img in images:
                 txt = ocrolib.fvariant(img,"txt","")
                 if os.path.exists(txt):