mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add "auto" language for TesseractOcr (#759)

Browse Source 
* Add "auto" language for TesseractOcr

Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>

* Add tesseract-ocr-script-latn installation for the "auto" language

Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>

* Modify "auto" language in TesseractOcr to initialize the script readers lazily

Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>

* Finalize script readers

Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>

* Fix script models prefix for Linux

Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>

---------

Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de>
This commit is contained in:
Pavel Denisov
2025-01-23 12:40:50 +01:00
committed by GitHub
parent c49b3526fb
commit 8543c22687
3 changed files with 68 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
docling/models/tesseract_ocr_model.py
View File

@@ -54,43 +54,56 @@ class TesseractOcrModel(BaseOcrModel):
# Initialize the tesseractAPI
_log.debug("Initializing TesserOCR: %s", tesseract_version)
lang = "+".join(self.options.lang)
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if any([l.startswith("script/") for l in tesserocr_languages]):
self.script_prefix = "script/"
else:
self.script_prefix = ""
tesserocr_kwargs = {
"psm": tesserocr.PSM.AUTO,
"init": True,
"oem": tesserocr.OEM.DEFAULT,
}
if self.options.path is not None:
tesserocr_kwargs["path"] = self.options.path
if lang == "auto":
self.reader = tesserocr.PyTessBaseAPI(
path=self.options.path,
lang=lang,
psm=tesserocr.PSM.AUTO,
init=True,
oem=tesserocr.OEM.DEFAULT,
**{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
)
else:
self.reader = tesserocr.PyTessBaseAPI(
lang=lang,
psm=tesserocr.PSM.AUTO,
init=True,
oem=tesserocr.OEM.DEFAULT,
**{"lang": lang} | tesserocr_kwargs,
)
self.reader_RIL = tesserocr.RIL
def __del__(self):
if self.reader is not None:
# Finalize the tesseractAPI
self.reader.End()
for script in self.script_readers:
self.script_readers[script].End()
def __call__(
self, conv_res: ConversionResult, page_batch: Iterable[Page]
) -> Iterable[Page]:
if not self.enabled:
yield from page_batch
return
import tesserocr
for page in page_batch:
assert page._backend is not None
if not page._backend.is_valid():
yield page
else:
with TimeRecorder(conv_res, "ocr"):
assert self.reader is not None
ocr_rects = self.get_ocr_rects(page)
@@ -106,20 +119,55 @@ class TesseractOcrModel(BaseOcrModel):
# Retrieve text snippets with their bounding boxes
self.reader.SetImage(high_res_image)
boxes = self.reader.GetComponentImages(
if self.options.lang == ["auto"]:
osd = self.reader.DetectOrientationScript()
# No text, probably
if osd is None:
continue
script = osd["script_name"]
if script == "Katakana" or script == "Hiragana":
script = "Japanese"
elif script == "Han":
script = "HanS"
elif script == "Korean":
script = "Hangul"
_log.debug(
f'Using model for the detected script "{script}"'
)
if script not in self.script_readers:
self.script_readers[script] = tesserocr.PyTessBaseAPI(
path=self.reader.GetDatapath(),
lang=f"{self.script_prefix}{script}",
psm=tesserocr.PSM.AUTO,
init=True,
oem=tesserocr.OEM.DEFAULT,
)
local_reader = self.script_readers[script]
local_reader.SetImage(high_res_image)
else:
local_reader = self.reader
boxes = local_reader.GetComponentImages(
self.reader_RIL.TEXTLINE, True
)
cells = []
for ix, (im, box, _, _) in enumerate(boxes):
# Set the area of interest. Tesseract uses Bottom-Left for the origin
self.reader.SetRectangle(
local_reader.SetRectangle(
box["x"], box["y"], box["w"], box["h"]
)
# Extract text within the bounding box
text = self.reader.GetUTF8Text().strip()
confidence = self.reader.MeanTextConf()
text = local_reader.GetUTF8Text().strip()
confidence = local_reader.MeanTextConf()
left = box["x"] / self.scale
bottom = box["y"] / self.scale
right = (box["x"] + box["w"]) / self.scale