From ffd160ce0eb25597f704000562213ba98ae0fdaf Mon Sep 17 00:00:00 2001
From: Hritik Vijay <hey@hritik.sh>
Date: Fri, 21 Jun 2024 17:01:03 +0530
Subject: [PATCH] Filters - Implement jqraw: filter  (use this to output nicer
 JSON format when selecting/filtering by JSON) (#2430)

---
 .../blueprint/tags/templates/edit-tag.html    |  2 +-
 changedetectionio/html_tools.py               | 17 +++++----
 .../processors/text_json_diff.py              |  2 +-
 changedetectionio/templates/edit.html         |  2 +-
 .../tests/test_jsonpath_jq_selector.py        | 36 +++++++++++++++----
 5 files changed, 42 insertions(+), 17 deletions(-)

diff --git a/changedetectionio/blueprint/tags/templates/edit-tag.html b/changedetectionio/blueprint/tags/templates/edit-tag.html
index 1d297c81..9f316c55 100644
--- a/changedetectionio/blueprint/tags/templates/edit-tag.html
+++ b/changedetectionio/blueprint/tags/templates/edit-tag.html
@@ -63,7 +63,7 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                             <ul>
                                 <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
                                 {% if jq_support %}
-                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>. Prefix <code>jqraw:</code> outputs the results as text instead of a JSON list.</li>
                                 {% else %}
                                 <li>jq support not installed</li>
                                 {% endif %}
diff --git a/changedetectionio/html_tools.py b/changedetectionio/html_tools.py
index a03653b9..ff5cedad 100644
--- a/changedetectionio/html_tools.py
+++ b/changedetectionio/html_tools.py
@@ -3,8 +3,6 @@ from bs4 import BeautifulSoup
 from inscriptis import get_text
 from jsonpath_ng.ext import parse
 from typing import List
-from inscriptis.css_profiles import CSS_PROFILES, HtmlElement
-from inscriptis.html_properties import Display
 from inscriptis.model.config import ParserConfig
 from xml.sax.saxutils import escape as xml_escape
 import json
@@ -196,12 +194,12 @@ def extract_element(find='title', html_content=''):
 
 #
 def _parse_json(json_data, json_filter):
-    if 'json:' in json_filter:
+    if json_filter.startswith("json:"):
         jsonpath_expression = parse(json_filter.replace('json:', ''))
         match = jsonpath_expression.find(json_data)
         return _get_stripped_text_from_json_match(match)
 
-    if 'jq:' in json_filter:
+    if json_filter.startswith("jq:") or json_filter.startswith("jqraw:"):
 
         try:
             import jq
@@ -209,10 +207,15 @@ def _parse_json(json_data, json_filter):
             # `jq` requires full compilation in windows and so isn't generally available
             raise Exception("jq not support not found")
 
-        jq_expression = jq.compile(json_filter.replace('jq:', ''))
-        match = jq_expression.input(json_data).all()
+        if json_filter.startswith("jq:"):
+            jq_expression = jq.compile(json_filter.removeprefix("jq:"))
+            match = jq_expression.input(json_data).all()
+            return _get_stripped_text_from_json_match(match)
 
-        return _get_stripped_text_from_json_match(match)
+        if json_filter.startswith("jqraw:"):
+            jq_expression = jq.compile(json_filter.removeprefix("jqraw:"))
+            match = jq_expression.input(json_data).all()
+            return '\n'.join(str(item) for item in match)
 
 def _get_stripped_text_from_json_match(match):
     s = []
diff --git a/changedetectionio/processors/text_json_diff.py b/changedetectionio/processors/text_json_diff.py
index e89e469d..1d60be63 100644
--- a/changedetectionio/processors/text_json_diff.py
+++ b/changedetectionio/processors/text_json_diff.py
@@ -18,7 +18,7 @@ urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 name = 'Webpage Text/HTML, JSON and PDF changes'
 description = 'Detects all text changes where possible'
-json_filter_prefixes = ['json:', 'jq:']
+json_filter_prefixes = ['json:', 'jq:', 'jqraw:']
 
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
diff --git a/changedetectionio/templates/edit.html b/changedetectionio/templates/edit.html
index 6d6d19fc..15cb3fd5 100644
--- a/changedetectionio/templates/edit.html
+++ b/changedetectionio/templates/edit.html
@@ -292,7 +292,7 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                             <ul>
                                 <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
                                 {% if jq_support %}
-                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>. Prefix <code>jqraw:</code> outputs the results as text instead of a JSON list.</li>
                                 {% else %}
                                 <li>jq support not installed</li>
                                 {% endif %}
diff --git a/changedetectionio/tests/test_jsonpath_jq_selector.py b/changedetectionio/tests/test_jsonpath_jq_selector.py
index 1202849f..55f46a0d 100644
--- a/changedetectionio/tests/test_jsonpath_jq_selector.py
+++ b/changedetectionio/tests/test_jsonpath_jq_selector.py
@@ -41,19 +41,26 @@ and it can also be repeated
     from .. import html_tools
 
     # See that we can find the second <script> one, which is not broken, and matches our filter
-    text = html_tools.extract_json_as_string(content, "json:$.offers.price")
-    assert text == "23.5"
+    text = html_tools.extract_json_as_string(content, "json:$.offers.priceCurrency")
+    assert text == '"AUD"'
+
+    text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
+    assert text == "5"
 
     # also check for jq
     if jq_support:
-        text = html_tools.extract_json_as_string(content, "jq:.offers.price")
-        assert text == "23.5"
+        text = html_tools.extract_json_as_string(content, "jq:.offers.priceCurrency")
+        assert text == '"AUD"'
 
         text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
         assert text == "5"
 
-    text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
-    assert text == "5"
+        text = html_tools.extract_json_as_string(content, "jqraw:.offers.priceCurrency")
+        assert text == "AUD"
+
+        text = html_tools.extract_json_as_string('{"id":5}', "jqraw:.id")
+        assert text == "5"
+
 
     # When nothing at all is found, it should throw JSONNOTFound
     # Which is caught and shown to the user in the watch-overview table
@@ -64,6 +71,9 @@ and it can also be repeated
         with pytest.raises(html_tools.JSONNotFound) as e_info:
             html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
 
+        with pytest.raises(html_tools.JSONNotFound) as e_info:
+            html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jqraw:.id")
+
 
 def test_unittest_inline_extract_body():
     content = """
@@ -291,6 +301,10 @@ def test_check_jq_filter(client, live_server):
     if jq_support:
         check_json_filter('jq:.boss.name', client, live_server)
 
+def test_check_jqraw_filter(client, live_server):
+    if jq_support:
+        check_json_filter('jqraw:.boss.name', client, live_server)
+
 def check_json_filter_bool_val(json_filter, client, live_server):
     set_original_response()
 
@@ -345,6 +359,10 @@ def test_check_jq_filter_bool_val(client, live_server):
     if jq_support:
         check_json_filter_bool_val("jq:.available", client, live_server)
 
+def test_check_jqraw_filter_bool_val(client, live_server):
+    if jq_support:
+        check_json_filter_bool_val("jq:.available", client, live_server)
+
 # Re #265 - Extended JSON selector test
 # Stuff to consider here
 # - Selector should be allowed to return empty when it doesnt match (people might wait for some condition)
@@ -491,4 +509,8 @@ def test_check_jsonpath_ext_filter(client, live_server):
 
 def test_check_jq_ext_filter(client, live_server):
     if jq_support:
-        check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)
\ No newline at end of file
+        check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)
+
+def test_check_jqraw_ext_filter(client, live_server):
+    if jq_support:
+        check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)