Python 3.5 support, tests for [ydataai#147] and XSS filter

.gitignore

@@ -68,4 +68,5 @@ target/
 .ipynb_checkpoints/
 ipynb_tmp/
 examples/*/*.csv
-examples/*/*.html
+examples/*/*.html
+*.parquet

docs/view/formatters.html

@@ -24,6 +24,7 @@ <h1 class="title">Module <code>pandas_profiling.view.formatters</code></h1>
 <details class="source">
 <summary>Source code</summary>
 <pre><code class="python">&#34;&#34;&#34;Formatters are utilities for formatting numbers and certain strings&#34;&#34;&#34;
+from jinja2.utils import escape
 
 
 def fmt_color(text: str, color: str) -&gt; str:
@@ -107,7 +108,7 @@ <h1 class="title">Module <code>pandas_profiling.view.formatters</code></h1>
     if type(value) in [float, int]:
         return fmt_numeric(value)
     else:
-        return str(value)
+        return str(escape(value))
 
 
 def hex_to_rgb(hex):
@@ -159,7 +160,7 @@ <h2 id="returns">Returns</h2>
     if type(value) in [float, int]:
         return fmt_numeric(value)
     else:
-        return str(value)</code></pre>
+        return str(escape(value))</code></pre>
 </details>
 </dd>
 <dt id="pandas_profiling.view.formatters.fmt_bytesize"><code class="name flex">

pandas_profiling/view/formatters.py

@@ -1,4 +1,5 @@
 """Formatters are utilities for formatting numbers and certain strings"""
+from jinja2.utils import escape
 
 
 def fmt_color(text: str, color: str) -> str:
@@ -82,7 +83,7 @@ def fmt(value) -> str:
     if type(value) in [float, int]:
         return fmt_numeric(value)
     else:
-        return str(value)
+        return str(escape(value))
 
 
 def hex_to_rgb(hex):

requirements-test.txt

@@ -2,3 +2,4 @@ pytest
 codecov
 pytest-cov
 nbval
+pyarrow

tests/issues/test_issue147.py

@@ -0,0 +1,20 @@
+from pathlib import Path
+
+import pandas as pd
+import requests
+
+from pandas_profiling import ProfileReport
+
+
+# https://github.com/pandas-profiling/pandas-profiling/issues/147
+def test_issue147(tmpdir):
+    file_name = Path(str(tmpdir)) / "userdata1.parquet"
+    data = requests.get(
+        "https://github.com/Teradata/kylo/raw/master/samples/sample-data/parquet/userdata2.parquet"
+    )
+    file_name.write_bytes(data.content)
+
+    df = pd.read_parquet(str(file_name), engine="pyarrow")
+    report = ProfileReport(df, title="PyArrow with Pandas Parquet Backend")
+    html = report.to_html()
+    assert type(html) == str and '<p class="h2">Dataset info</p>' in html

tests/test_describe.py

@@ -59,8 +59,20 @@ def recoding_data():
 
 def test_recoding_reject(recoding_data):
     results = describe(recoding_data)
-    assert results["variables"]["y"]["type"] == Variable.S_TYPE_RECODED, "Type is wrong"
-    assert results["variables"]["y"]["correlation_var"] == "x", "Values should be equal"
+    assert (
+        results["variables"]["y"]["type"] == Variable.S_TYPE_RECODED
+        and results["variables"]["x"]["type"] == Variable.TYPE_CAT
+    ) or (
+        results["variables"]["x"]["type"] == Variable.S_TYPE_RECODED
+        and results["variables"]["y"]["type"] == Variable.TYPE_CAT
+    ), "Type is wrong"
+    assert (
+        "correlation_var" in results["variables"]["y"]
+        and results["variables"]["y"]["correlation_var"] == "x"
+    ) or (
+        "correlation_var" in results["variables"]["x"]
+        and results["variables"]["x"]["correlation_var"] == "y"
+    ), "Values should be equal"
 
     expected_results = {
         "n_cells_missing": 0.0,
@@ -89,8 +101,21 @@ def test_cramers_reject(recoding_data):
     config["correlations"]["cramers"].set(True)
     results = describe(recoding_data)
 
-    assert results["variables"]["y"]["type"] == Variable.S_TYPE_CORR, "Type is wrong"
-    assert results["variables"]["y"]["correlation_var"] == "x", "Values should be equal"
+    # The order of dicts is not preserved in Python 3.5 and not guaranteed in Python 3.6
+    assert (
+        results["variables"]["y"]["type"] == Variable.S_TYPE_CORR
+        and results["variables"]["x"]["type"] == Variable.TYPE_CAT
+    ) or (
+        results["variables"]["x"]["type"] == Variable.S_TYPE_CORR
+        and results["variables"]["y"]["type"] == Variable.TYPE_CAT
+    ), "Type is wrong"
+    assert (
+        "correlation_var" in results["variables"]["y"]
+        and results["variables"]["y"]["correlation_var"] == "x"
+    ) or (
+        "correlation_var" in results["variables"]["x"]
+        and results["variables"]["x"]["correlation_var"] == "y"
+    ), "Values should be equal"
 
     expected_results = {
         "n_cells_missing": 0.0,