(release): A2I custom and IDP Mortgage

README.md

@@ -63,7 +63,7 @@ Once the SageMaker Studio IDE has fully loaded in your browser, you can clone th
 * Next, clone this repository using 
 
 ```  
-git clone <repo_url> idp_workshop
+git clone https://github.com/aws-samples/aws-ai-intelligent-document-processing idp_workshop
 ```
 
 * Once the repository is cloned, a direcotry named `idp_workshop` will appear in the "File Browser" on the left panel of SageMaker Studio IDE

a2idata/a2i-bi-sample-data.csv

@@ -0,0 +1,36 @@
+timestamp,doc_id,condition_category,condition_setting,field_name,field_value,human_loop_name,reviewer,process_method
+2022/07/01,9.34932E+13,LengthCheck,^[0-9a-zA-Z]{16}$,dln,9.34932E+13,custom-loop-a8e97e82-2b71-43cc-9b9f-9f3cc1f17bc5,Reviewer 1,manu
+2022/07/01,93493188018523,Confidence,99,d.employer_id,98.06,custom-loop-a8e97e82-2b71-43cc-9b9f-9f3cc1f17bc5,Reviewer 1,manu
+2022/07/02,93493188018524,Required,,dln,,custom-loop-8703c751-4a83-4cd8-b19e-81ea8d09a1d2,Reviewer 2,manu
+2022/07/02,93493188018525,LengthCheck,,e.phone_number,123,custom-loop-8703c751-4a83-4cd8-b19e-81ea8d09a1w3,Reviewer 1,manu
+2022/07/02,93493188018525,Required,,dln,,custom-loop-8703c751-4a83-4cd8-b19e-81ea8d09a1w3,Reviewer 1,manu
+2022/07/03,93493188018526,Required,,dln,,custom-loop-8703c751-4a83-4cd8-b19e-81ea8d09a13d,Reviewer 1,manu
+2022/07/03,93493188018527,Confidence,,dln,94,custom-loop-8703c751-4a83-4cd8-b19e-81ea8d09a134,Reviewer 3,manu
+2022/07/04,93493188018528,LengthCheck,,omb_no,,custom-loop-8703c751-4a83-4cd8-b19e-81ea8d09a1xs,Reviewer 3,manu
+2022/07/01,93493188018529,,,,,,,auto
+2022/07/01,93493188018530,,,,,,,auto
+2022/07/01,93493188018531,,,,,,,auto
+2022/07/01,93493188018532,,,,,,,auto
+2022/07/01,93493188018533,,,,,,,auto
+2022/07/02,93493188018534,,,,,,,auto
+2022/07/02,93493188018535,,,,,,,auto
+2022/07/02,93493188018536,,,,,,,auto
+2022/07/02,93493188018537,,,,,,,auto
+2022/07/02,93493188018538,,,,,,,auto
+2022/07/02,93493188018539,,,,,,,auto
+2022/07/03,93493188018540,,,,,,,auto
+2022/07/03,93493188018541,,,,,,,auto
+2022/07/03,93493188018542,,,,,,,auto
+2022/07/03,93493188018543,,,,,,,auto
+2022/07/03,93493188018544,,,,,,,auto
+2022/07/03,93493188018545,,,,,,,auto
+2022/07/03,93493188018546,,,,,,,auto
+2022/07/03,93493188018546,,,,,,,auto
+2022/07/03,93493188018547,,,,,,,auto
+2022/07/03,93493188018548,,,,,,,auto
+2022/07/03,93493188018549,,,,,,,auto
+2022/07/04,93493188018550,,,,,,,auto
+2022/07/04,93493188018551,,,,,,,auto
+2022/07/04,93493188018552,,,,,,,auto
+2022/07/04,93493188018553,,,,,,,auto
+2022/07/04,93493188018554,,,,,,,auto

a2idata/a2i-custom-ui.html

@@ -0,0 +1,159 @@
+<script src="https://assets.crowd.aws/crowd-html-elements.js"></script>
+
+<link rel="stylesheet" href="https://s3.amazonaws.com/smgtannotation/web/static/css/1.3fc3007b.chunk.css">
+<link rel="stylesheet" href="https://s3.amazonaws.com/smgtannotation/web/static/css/main.9504782e.chunk.css">
+<link href="/static/css/1.fe2e351b.chunk.css" rel="stylesheet">
+<link href="/static/css/main.2b80d815.chunk.css" rel="stylesheet">
+<style>
+  .wrapper {
+    position:relative;
+    display:block; /* <= shrinks container to image size */
+    overflow-y: scroll;
+    max-height:1000px;
+    background-color: #e9ecec;
+    padding: 30px;
+    border:red 10px;
+  }
+  .img-overlay-wrap {
+    position: relative;
+    display: inline-block; /* <= shrinks container to image size */
+    transition: transform 150ms ease-in-out;
+    overflow-y: scroll;
+    background-color: #e9ecec;
+   }
+
+  .img-overlay-wrap img { /* <= optional, for responsiveness */
+     display: block;
+     max-width: 800;
+     height: auto;
+     box-shadow: 0 0 20px rgba(0, 0, 0, 0.15);
+  }
+
+  .img-overlay-wrap svg {
+    position: absolute;
+    top: 0;
+    left: 0;
+  }
+
+  .img-overlay-wrap svg rect {
+      stroke:#009879;
+      stroke-width: 2;
+      fill: #009879; 
+      fill-opacity: 20%;
+  }
+
+  .styled-table input {
+    width:250px;
+    height: 100px;
+    vertical-align: top;
+  }
+  .styled-table {
+    border-collapse: collapse;
+    margin: 10px 0;
+    font-size: 0.9em;
+    font-family: sans-serif;
+    width:100%;
+    box-shadow: 0 0 20px rgba(0, 0, 0, 0.15);
+  }
+  .styled-table thead tr {
+      background-color: #009879;
+      color: #ffffff;
+      text-align: left;
+  }
+  .styled-table th,
+  .styled-table td {
+      padding: 12px 15px;
+      vertical-align: top;
+  }
+  .styled-table tbody tr {
+      border-bottom: 1px solid #dddddd;
+  }
+
+  .styled-table tbody tr:nth-of-type(even) {
+      background-color: #f3f3f3;
+  }
+
+  .styled-table tbody tr:last-of-type {
+      border-bottom: 2px solid #009879;
+  }
+  .styled-table tbody tr.active-row {
+      font-weight: bold;
+      color: #009879;
+  }  
+  </style>
+  <script>
+    function condition_over(idx) {
+      document.getElementById("rectm_" + idx).style = "stroke-width:2px; fill: transparent; stroke: #9e4064; fill: #c5a7be;";
+      document.getElementById("tr_" + idx).class = "active-row"
+    }
+    function condition_out(idx) {
+      document.getElementById("rectm_" + idx).style = "stroke-width: 2;fill: #009879; fill-opacity: 20%;";
+      document.getElementById("tr_" + idx).class = ""
+    }
+   </script>
+<div id='document-text' style="display: none;">
+  {{ task.input.text }}
+</div>
+<div id='document-image' style="display: none;">
+        {{ task.input.s3.url | grant_read_access }}
+</div>
+
+<table>
+  <tr>
+    <td style="vertical-align: top;">
+      <div class="wrapper">
+      <div class="img-overlay-wrap">
+        <img src="{{ task.input.s3.url | grant_read_access }}">
+        <svg viewBox="0 0 {{task.input.s3.image_width}} {{task.input.s3.image_height}}">
+          {% for b in task.input.Results.ConditionMissed %}
+            {% if b.block != null %}
+            <rect id="rectm_{{b.index}}" width="{{ b.block.Geometry.BoundingBox.Width | times: task.input.s3.image_width }}" height="{{ b.block.Geometry.BoundingBox.Height | times: task.input.s3.image_height }}" x="{{ b.block.Geometry.BoundingBox.Left | times: task.input.s3.image_width }}" y="{{ b.block.Geometry.BoundingBox.Top | times: task.input.s3.image_height }}"></rect>
+            {% endif %}
+          {% endfor %}
+        </svg>
+      </div>
+    </div>
+    </td>
+    <td>&nbsp;&nbsp;&nbsp;</td>
+    <td style="vertical-align: top; padding: 20px;">
+      <crowd-form>
+        <div>
+          <h3>Instructions</h3>
+          <p>Please review the extracted result, and make corrections where appropriate. </p>
+      </div>
+      <br>
+      <h3> Missed Conditions </h3>
+      <table class="styled-table">
+        <thead>
+        <tr>
+          <th style="width:250px">DESCRIPTION</th>
+          <th>ACTUAL VALUE</th>
+          <th>YOUR VALUE</th>
+          <th>CHANGE REASON</th>
+        </tr>
+      </thead>
+        <tbody>
+          {% for r in task.input.Results.ConditionMissed %}
+
+              <tr id="tr_{{r.index}}" onmouseover="javascript:condition_over( {{r.index}} )" onmouseout="javascript:condition_out({{r.index}})">
+                <td title="Field name: {{r.field_name}} ({{ r.condition_category }})">{{ r.message }}</td>
+                <td>{{ r.field_value }}</td>
+                <td>
+                  <p>
+                  <input type="text" name="True Value {{r.index}}" placeholder="Enter your value" />
+                  </p>
+                 </td>
+                 <td>
+                  <p>
+                  <input type="text" name="Change Reason {{r.index}}" placeholder="Explain why you changed the value" />
+                  </p>
+                 </td>
+              </tr>
+
+            {% endfor %}
+          </tbody>
+        </table>
+        </crowd-form>
+    </td>
+  </tr>
+</table>

a2idata/condition.py

@@ -0,0 +1,100 @@
+from enum import Enum
+import re
+
+class Condition:
+    _data = None
+    _conditions = None
+    _result = None
+
+    def __init__(self, data, conditions):
+        self._data = data
+        self._conditions = conditions
+
+    def check(self, field_name, obj):
+        r,s = [],[]
+        for c in self._conditions:
+            # Matching field_name or field_name_regex
+            condition_setting = c.get("condition_setting")
+            if c["field_name"] == field_name \
+                    or (c.get("field_name") is None and c.get("field_name_regex") is not None and re.search(c.get("field_name_regex"), field_name)):
+                field_value, block = None, None
+                if obj is not None:
+                    field_value = obj.get("value")
+                    block = obj.get("block")
+                    confidence = obj.get("confidence")
+
+                if c["condition_type"] == "Required" \
+                        and (obj is None or field_value is None or len(str(field_value)) == 0):
+                    r.append({
+                                "message": f"The required field [{field_name}] is missing.",
+                                "field_name": field_name,
+                                "field_value": field_value,
+                                "condition_type": str(c["condition_type"]),
+                                "condition_setting": condition_setting,
+                                "condition_category":c["condition_category"],
+                                "block": block
+                            })
+                elif c["condition_type"] == "ConfidenceThreshold" \
+                    and c["condition_setting"] is not None and float(confidence) < float(c["condition_setting"]):
+                    r.append({
+                                "message": f"The field [{field_name}] confidence score {confidence} is lower than the threshold {c['condition_setting']}",
+                                "field_name": field_name,
+                                "field_value": field_value,
+                                "condition_type": str(c["condition_type"]),
+                                "condition_setting": condition_setting,
+                                "condition_category":c["condition_category"],
+                                "block": block
+                            })
+                elif field_value is not None and c["condition_type"] == "ValueRegex" and condition_setting is not None \
+                        and re.search(condition_setting, str(field_value)) is None:
+                    r.append({
+                                "message": f"{c['description']}",
+                                "field_name": field_name,
+                                "field_value": field_value,
+                                "condition_type": str(c["condition_type"]),
+                                "condition_setting": condition_setting,
+                                "condition_category":c["condition_category"],
+                                "block": block
+                            })
+
+                # field has condition defined and sastified
+                s.append(
+                    {
+                        "message": f"{c['description']}",
+                        "field_name": field_name,
+                        "field_value": field_value,
+                        "condition_type": str(c["condition_type"]),
+                        "condition_setting": condition_setting,
+                        "condition_category":c["condition_category"],
+                        "block": block
+                    })
+
+        return r, s
+
+    def check_all(self):
+        if self._data is None or self._conditions is None:
+            return None
+
+        broken_conditions = []
+        satisfied_conditions = []
+        for key, obj in self._data.items():
+            value = None
+            if obj is not None:
+                value = obj.get("value")
+
+            if value is not None and type(value)==str:
+                value = value.replace(' ','')
+
+            r, s = self.check(key, obj)
+            if r and len(r) > 0:
+                broken_conditions += r
+            if s and len(s) > 0:
+                satisfied_conditions += s
+
+
+        # apply index
+        idx = 0
+        for r in broken_conditions:
+            idx += 1
+            r["index"] = idx
+        return broken_conditions, satisfied_conditions

dist/idp-deploy.yaml

@@ -106,10 +106,18 @@ Resources:
                   - textract:GetDocumentTextDetection
                   - textract:GetDocumentAnalysis
                   - textract:AnalyzeDocument
+                  - textract:AnalyzeID
+                  - textract:AnalyzeExpense
                   - textract:DetectDocumentText
                   - textract:StartDocumentAnalysis
                   - textract:StartDocumentTextDetection
                   - comprehend:DetectEntities
+                  - comprehend:DetectPiiEntities
+                  - comprehend:ContainsPiiEntities
+                  - comprehend:DescribePiiEntitiesDetectionJob
+                  - comprehend:ListPiiEntitiesDetectionJobs
+                  - comprehend:StartPiiEntitiesDetectionJob
+                  - comprehend:StopPiiEntitiesDetectionJob
                   - comprehend:StartEntitiesDetectionJob
                   - comprehend:ClassifyDocument
                   - comprehend:DescribeDocumentClassificationJob