Upload 2 files

gingerit.py

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+import requests
+import cloudscraper
+URL = "https://services.gingersoftware.com/Ginger/correct/jsonSecured/GingerTheTextFull"  # noqa
+API_KEY = "6ae0c3a0-afdc-4532-a810-82ded0054236"
+
+
+class GingerIt(object):
+    def __init__(self):
+        self.url = URL
+        self.api_key = API_KEY
+        self.api_version = "2.0"
+        self.lang = "US"
+
+    def parse(self, text, verify=True):
+        #session = requests.Session()
+        session = cloudscraper.create_scraper()
+        request = session.get(
+            self.url,
+            params={
+                "lang": self.lang,
+                "apiKey": self.api_key,
+                "clientVersion": self.api_version,
+                "text": text,
+            },
+            verify=verify,
+        )
+        data = request.json()
+        return self._process_data(text, data)
+
+    @staticmethod
+    def _change_char(original_text, from_position, to_position, change_with):
+        return "{}{}{}".format(
+            original_text[:from_position], change_with, original_text[to_position + 1 :]
+        )
+
+    def _process_data(self, text, data):
+        result = text
+        corrections = []
+        
+        for suggestion in reversed(data["Corrections"]):
+            start = suggestion["From"]
+            end = suggestion["To"]
+
+            if suggestion["Suggestions"]:
+                suggest = suggestion["Suggestions"][0]
+                result = self._change_char(result, start, end, suggest["Text"])
+
+                corrections.append(
+                    {
+                        "start": start,
+                        "text": text[start : end + 1],
+                        "correct": suggest.get("Text", None),
+                        "definition": suggest.get("Definition", None),
+                    }
+                )
+
+        return {"text": text, "result": result, "corrections": corrections}

output_beautify.py

@@ -0,0 +1,36 @@
+import re
+from gingerit import GingerIt
+import pysbd
+
+
+segmentor = pysbd.Segmenter(language="en", clean=False)
+subsegment_re = r'[^;:\n•]+[;,:\n•]?\s*'
+
+
+def clean_text(text):
+    s1 = re.sub("\*", " ", text)
+    s2 = re.sub("\|"," ",s1)
+    s3 = re.sub("--+"," ",s2)
+    s4 = re.sub("\#", " ", s3)
+    s5 = re.sub("\n", " ", s4)
+    s6 = re.sub(" +"," ",s5)
+    return s6
+
+
+def runGinger(par):
+    par = clean_text(par)
+    fixed = []
+    for sentence in segmentor.segment(par):
+        if len(sentence) < 300:
+            fixed.append(GingerIt().parse(sentence)['result'])
+        else:
+            subsegments = re.findall(subsegment_re, sentence)
+            if len(subsegments) == 1 or any(len(v) < 300 for v in subsegments):
+                print(f'Skipped: {sentence}')
+                fixed.append(sentence)
+            else:
+                res = []
+                for s in subsegments:
+                    res.append(GingerIt().parse(s)['result'])
+                fixed.append("".join(res))
+    return " ".join(fixed)