Cut some stuff

README.md

@@ -1,10 +1,10 @@
 ---
-title: Hive OCR
+title: Hive OCR simple
 emoji: 🦀
 colorFrom: pink
 colorTo: blue
 sdk: gradio
-sdk_version: 2.9.1
+sdk_version: 3.14.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,40 +1,43 @@
+from codecs import encode, decode
 import requests
 import gradio as gr
-import pandas as pd
-from PIL import Image, ImageDraw
+
 
 def infer(im):
-  im.save('converted.png')
-  url = 'https://ajax.thehive.ai/api/demo/classify?endpoint=text_recognition'
-  files = {
-      'image': ('converted.png', open('converted.png', 'rb'), 'image/png'),
-      'model_type': (None, 'detection'),
-      'media_type': (None, 'photo'),
-  }
-  headers = {
-      'referer': 'https://thehive.ai/'
-  }
-  r = requests.post(url, headers=headers, files=files)
-  res = r.json()
-  print(r, res)
-  img = im.convert('RGB')
-
-  words = []
-  draw = ImageDraw.Draw(img,'RGBA')
-  for output in res['response']['output']:
-    for poly in output['bounding_poly']:
-      words += [c['class'] for c in poly['classes']]
-      draw.rectangle((poly['dimensions']['left']-2,poly['dimensions']['top']-2,poly['dimensions']['right']+2,poly['dimensions']['bottom']+2), outline=(0,255,0,255), fill=(0,255,0,50),width=2)
-
-  img.save('result.png')
-  return 'result.png', '\n'.join([o['block_text'] for o in res['response']['output']]), pd.DataFrame(words)
+    im.save("converted.png")
+    url = "https://ajax.thehive.ai/api/demo/classify?endpoint=text_recognition"
+    files = {
+        "image": ("converted.png", open("converted.png", "rb"), "image/png"),
+        "model_type": (None, "detection"),
+        "media_type": (None, "photo"),
+    }
+    headers = {"referer": "https://thehive.ai/"}
+
+    res = requests.post(url, headers=headers, files=files)
+
+    text = ""
+    blocks = []
+    for output in res.json()["response"]["output"]:
+        text += output["block_text"]
+        for poly in output["bounding_poly"]:
+            blocks.append(
+                {
+                    "text": "".join([c["class"] for c in poly["classes"]]),
+                    "rect": poly["dimensions"],
+                }
+            )
+
+    text = decode(encode(text, "latin-1", "backslashreplace"), "unicode-escape")
+
+    return text, blocks
+
 
 iface = gr.Interface(
     fn=infer,
-    title="Hive OCR",
-    description="Demo for Hive OCR.Transcribe and analyze media depicting typed, written, or graphic text",
-    inputs=[gr.inputs.Image(label='image', type='pil')],
-    outputs=['image', 'text', gr.outputs.Dataframe(headers=['word'])],
-    examples=['testocr.png', 'receipt.webp', '20131216170659.jpg'],
-    article="<a href=\"https://thehive.ai/hive-ocr-solutions\">Hive OCR</a>",
-).launch()
+    title="Hive OCR simple",
+    description="Demo for Hive OCR. Transcribe and analyze media depicting typed, written, or graphic text",
+    inputs=[gr.Image(type="pil")],
+    outputs=["text", "json"],
+    examples=["20131216170659.jpg"],
+    article='<a href="https://thehive.ai/hive-ocr-solutions">Hive OCR</a>',
+).launch()