make de_identify_results List[List[Replacement]]

docs/source/redact/redacting_text.rst

@@ -67,56 +67,52 @@ This produces the following output.  Note that the 'idx' property denotes the po
 
 .. code-block:: console
 
-    [ORGANIZATION_P5XLAH] was founded in [DATE_TIME_0FW53]
-    [NAME_GIVEN_HI1h7] [NAME_FAMILY_5oMl28] is a person
-    {
-        "start": 0,
-        "end": 5,
-        "new_start": 0,
-        "new_end": 21,
-        "label": "ORGANIZATION",
-        "text": "Tonic",
-        "score": 0.9,
-        "language": "en",
-        "new_text": "[ORGANIZATION_P5XLAH]",
-        "idx": 0
-    }
-    {
-        "start": 21,
-        "end": 25,
-        "new_start": 37,
-        "new_end": 54,
-        "label": "DATE_TIME",
-        "text": "2018",
-        "score": 0.9,
-        "language": "en",
-        "new_text": "[DATE_TIME_0FW53]",
-        "idx": 0
-    }
-    {
-        "start": 0,
-        "end": 4,
-        "new_start": 0,
-        "new_end": 18,
-        "label": "NAME_GIVEN",
-        "text": "John",
-        "score": 0.9,
-        "language": "en",
-        "new_text": "[NAME_GIVEN_HI1h7]",
-        "idx": 1
-    }
-    {
-        "start": 5,
-        "end": 10,
-        "new_start": 19,
-        "new_end": 39,
-        "label": "NAME_FAMILY",
-        "text": "Smith",
-        "score": 0.9,
-        "language": "en",
-        "new_text": "[NAME_FAMILY_5oMl28]",
-        "idx": 1
-    }
+[ORGANIZATION_5Ve7OH] was founded in [DATE_TIME_DnuC1]
+{
+  "start": 0,
+  "end": 5,
+  "new_start": 0,
+  "new_end": 21,
+  "label": "ORGANIZATION",
+  "text": "Tonic",
+  "score": 0.9,
+  "language": "en",
+  "new_text": "[ORGANIZATION_5Ve7OH]"
+}
+{
+  "start": 21,
+  "end": 25,
+  "new_start": 37,
+  "new_end": 54,
+  "label": "DATE_TIME",
+  "text": "2018",
+  "score": 0.9,
+  "language": "en",
+  "new_text": "[DATE_TIME_DnuC1]"
+}
+[NAME_GIVEN_dySb5] [NAME_FAMILY_7w4Db3] is a person
+{
+  "start": 0,
+  "end": 4,
+  "new_start": 0,
+  "new_end": 18,
+  "label": "NAME_GIVEN",
+  "text": "John",
+  "score": 0.9,
+  "language": "en",
+  "new_text": "[NAME_GIVEN_dySb5]"
+}
+{
+  "start": 5,
+  "end": 10,
+  "new_start": 19,
+  "new_end": 39,
+  "label": "NAME_FAMILY",
+  "text": "Smith",
+  "score": 0.9,
+  "language": "en",
+  "new_text": "[NAME_FAMILY_7w4Db3]"
+}
 
 Redact JSON data
 ----------------

tonic_textual/classes/common_api_responses/replacement.py

@@ -37,8 +37,6 @@ class Replacement(dict):
     xml_path : Optional[str]
         The xpath of the entity in the original XML document. This is only present
         if the input text was an XML document.  NOTE: Arrays in xpath are 1-based
-    idx : Optional[int]
-        The index in the original bulk text array to which the NER result corresponds.  NOTE: This is only used when calling our bulk redaction methods
     """
 
     def __init__(
@@ -55,7 +53,6 @@ def __init__(
         example_redaction: Optional[str] = None,
         json_path: Optional[str] = None,
         xml_path: Optional[str] = None,
-        idx: Optional[int] = None,
     ):
         self.start = start
         self.end = end
@@ -69,7 +66,6 @@ def __init__(
         self.example_redaction = example_redaction
         self.json_path = json_path
         self.xml_path = xml_path
-        self.idx = idx
 
         dict.__init__(
             self,
@@ -89,7 +85,6 @@ def __init__(
             ),
             **({} if json_path is None else {"json_path": json_path}),
             **({} if xml_path is None else {"xml_path": xml_path}),
-            **({} if idx is None else {"idx": idx}),
         )
 
     def describe(self) -> str:
@@ -114,6 +109,4 @@ def to_dict(self) -> Dict:
             out["json_path"] = self.json_path
         if self.xml_path is not None:
             out["xml_path"] = self.xml_path
-        if self.idx is not None:
-            out["idx"] = self.idx
         return out

tonic_textual/classes/redact_api_responses/bulk_redaction_response.py

@@ -39,9 +39,13 @@ def __init__(
 
     def describe(self) -> str:
 
-        result = '\n'.join(self.bulk_redacted_text) + '\n'
-        for x in self.de_identify_results:
-            result += f"{x.describe()}\n"
+        result = ""
+        for redacted_text, de_id_res in zip(
+            self.bulk_redacted_text, self.de_identify_results
+        ):
+            result += f"{redacted_text}\n"
+            for replacement in de_id_res:
+                result += f"{replacement.describe()}\n"
         return result
 
     def get_usage(self):

tonic_textual/redact_api.py

@@ -703,23 +703,23 @@ def send_redact_bulk_request(
             if e.response.status_code == 400:
                 raise InvalidJsonForRedactionRequest(e.response.text)
             raise e
-
-        de_id_results = [
-            Replacement(
-                start=x["start"],
-                end=x["end"],
-                new_start=x.get("newStart"),
-                new_end=x.get("newEnd"),
-                label=x["label"],
-                text=x["text"],
-                new_text=x.get("newText"),
-                score=x["score"],
-                language=x.get("language"),
-                example_redaction=x.get("exampleRedaction"),
-                idx=x.get("idx")
+
+        de_id_results = [[] for i in range(len(response["bulkText"]))]
+        for x in response["deIdentifyResults"]:
+            de_id_results[x["idx"]].append(
+                Replacement(
+                    start=x["start"],
+                    end=x["end"],
+                    new_start=x.get("newStart"),
+                    new_end=x.get("newEnd"),
+                    label=x["label"],
+                    text=x["text"],
+                    new_text=x.get("newText"),
+                    score=x["score"],
+                    language=x.get("language"),
+                    example_redaction=x.get("exampleRedaction"),
+                )
             )
-            for x in response["deIdentifyResults"]
-        ]
 
         return BulkRedactionResponse(
             response["bulkText"],