From 5f5c6dc7882c6894d74fd7ee660f8a7d0b61565a Mon Sep 17 00:00:00 2001
From: Bee Webb <bee.webb@opendataservices.coop>
Date: Tue, 20 Aug 2024 13:25:38 +0000
Subject: [PATCH] xml input: Ensure namespaces don't break sheet titles

Namespaces contain colons which aren't permitted in Excel sheet names.
---
 CHANGELOG.md                                   |  1 +
 flattentool/schema.py                          |  2 +-
 flattentool/tests/fixtures/iati_namespaces.xml | 16 ++++++++++++++++
 flattentool/tests/test_init.py                 | 12 +++++++++++-
 4 files changed, 29 insertions(+), 2 deletions(-)
 create mode 100644 flattentool/tests/fixtures/iati_namespaces.xml

diff --git a/CHANGELOG.md b/CHANGELOG.md
index fce92a3..4010229 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 ### Fixed
 
 - Ignore null characters in the input CSV file when getting non-header rows
+- When unflatteneing XML, avoid errors due to namespaces causing colons in sheet names, by replacing them with dashes https://github.com/OpenDataServices/flatten-tool/pull/456
 
 ### Changed
 
diff --git a/flattentool/schema.py b/flattentool/schema.py
index 9110e8b..4f01722 100644
--- a/flattentool/schema.py
+++ b/flattentool/schema.py
@@ -42,7 +42,7 @@ def make_sub_sheet_name(
             x[:truncation_length] for x in parent_path.split(path_separator) if x != "0"
         )
         + property_name
-    )
+    ).replace(":", "-")
 
 
 class TitleLookup(UserDict):
diff --git a/flattentool/tests/fixtures/iati_namespaces.xml b/flattentool/tests/fixtures/iati_namespaces.xml
new file mode 100644
index 0000000..3a2defe
--- /dev/null
+++ b/flattentool/tests/fixtures/iati_namespaces.xml
@@ -0,0 +1,16 @@
+<?xml version='1.0' encoding='utf-8'?>
+<iati-activities xmlns:customns="http://example.com/2">
+  <!--XML generated by flatten-tool-->
+  <iati-activity xmlns:customns="http://example.com/1" last-updated-datetime="2011-10-01T00:00:00+00:00">
+    <customns:test>
+      <customns:part>two</customns:part>
+      <customns:part>two</customns:part>
+    </customns:test>
+  </iati-activity>
+  <iati-activity last-updated-datetime="2016-01-01T00:00:00+00:00">
+    <customns:test>
+      <customns:part>three</customns:part>
+      <customns:part>four</customns:part>
+    </customns:test>
+  </iati-activity>
+</iati-activities>
diff --git a/flattentool/tests/test_init.py b/flattentool/tests/test_init.py
index 0f382dc..35829f4 100644
--- a/flattentool/tests/test_init.py
+++ b/flattentool/tests/test_init.py
@@ -7,7 +7,7 @@
 
 import pytest
 
-from flattentool import decimal_datetime_default, unflatten
+from flattentool import decimal_datetime_default, flatten, unflatten
 
 
 def original_cell_and_row_locations(data):
@@ -1452,3 +1452,13 @@ def test_commands_id_name(tmpdir, input_format):
         ],
         "some": "data",
     }
+
+
+def test_flatten_xml(tmpdir):
+    flatten(
+        "flattentool/tests/fixtures/iati_namespaces.xml",
+        output_name=tmpdir.join("flattened_xml").strpath,
+        id_name="iati-identifier",
+        root_list_path="iati-activity",
+        xml=True,
+    )