Merge pull request #66 from deardurham/add_count

Start parsing offense record count

README.md

@@ -52,10 +52,22 @@ Example output:
 
 Pre-requisites:
 
+Mac
 ```
 brew cask install pdftotext
 ```
 
+Ubuntu
+```
+sudo apt-get install -y poppler-utils
+```
+
+```
+wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.04.tar.gz \
+    && tar -xvf xpdf-tools-linux-4.04.tar.gz \
+    && cp xpdf-tools-linux-4.04/bin64/pdftotext /usr/local/bin/pdftotext-4
+```
+
 Setup:
 
 ```bash
@@ -66,7 +78,7 @@ pip install -e .
 Read CIPRS PDF:
 
 ```
-python ciprs_-eader.py ./cypress-example.pdf
+python ciprs_reader.py ./cypress-example.pdf
 ```
 
 Run Jupyter:

ciprs_reader/parser/section/offense.py

@@ -50,6 +50,7 @@ def clean(self, matches):
 
     def extract(self, matches, report):
         record = {
+            "Count": matches["num"],
             "Action": matches["action"],
             "Description": matches["desc"],
             "Severity": matches["severity"],

tests/parsers/test_offense.py

@@ -21,6 +21,7 @@ def test_offense_record_charged_with_number(report, state):
     """
     matches = offense.OffenseRecordRowWithNumber(report, state).match(string)
     assert matches is not None, "Regex match failed"
+    assert matches["num"] == "54"
     assert matches["action"] == "CHARGED"
     assert matches["desc"] == "SPEEDING(80 mph in a 65 mph zone)"
     assert matches["severity"] == "INFRACTION"

tests/test_records/expected_output/test_redacted_1.json

@@ -19,6 +19,7 @@
             {
                 "Records": [
                     {
+                        "Count": "01",
                         "Action": "CHARGED",
                         "Description": "POSSESS MARIJUANA UP TO 1/2 OZ",
                         "Severity": "MISDEMEANOR",