From 0cb7fcca204987ab87f6cae21ef5304a8e2a1603 Mon Sep 17 00:00:00 2001
From: Daniel McDonald <danielmcdonald@ucsd.edu>
Date: Tue, 7 May 2024 08:57:05 -0700
Subject: [PATCH] Issue 957 (#963)

* TST: regression test for issue #957

* BUG: update_ids data type width was sensitive to strict setting, issue #957

* DOC: mention of issue #957
---
 ChangeLog.md             |  1 +
 biom/table.py            |  7 ++++++-
 biom/tests/test_table.py | 10 ++++++++++
 3 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/ChangeLog.md b/ChangeLog.md
index 6c8e1d4d..5c86c2b6 100644
--- a/ChangeLog.md
+++ b/ChangeLog.md
@@ -12,6 +12,7 @@ Bug Fixes:
 
 * Fixed an edge case on in `align_tree` when a feature was empty, see issue [#948](https://github.com/biocore/biom-format/issues/948)
 * In `subsample(..., with_replacement=True)`, it was possible to trigger a numerical stability on sum, see issue [#952](https://github.com/biocore/biom-format/issues/952)
+* `update_ids(..., strict=False)` could yield truncated IDs, see issue [#957](https://github.com/biocore/biom-format/issues/957)
 
 Performance improvements:
 
diff --git a/biom/table.py b/biom/table.py
index 0b6b32a0..7e4d2d00 100644
--- a/biom/table.py
+++ b/biom/table.py
@@ -1422,7 +1422,12 @@ def update_ids(self, id_map, axis='sample', strict=True, inplace=True):
         >>> print(updated_table.ids(axis='sample'))
         ['s1.1' 's2.2' 's3.3']
         """
-        str_dtype = 'U%d' % max([len(v) for v in id_map.values()])
+        max_str_len = max([len(v) for v in id_map.values()])
+        if not strict:
+            ids = self.ids(axis=axis)
+            max_str_len = max(max_str_len, max([len(i) for i in ids]))
+
+        str_dtype = 'U%d' % max_str_len
         updated_ids = zeros(self.ids(axis=axis).size, dtype=str_dtype)
         for idx, old_id in enumerate(self.ids(axis=axis)):
             if strict and old_id not in id_map:
diff --git a/biom/tests/test_table.py b/biom/tests/test_table.py
index 5998638f..52c53fc0 100644
--- a/biom/tests/test_table.py
+++ b/biom/tests/test_table.py
@@ -2412,6 +2412,16 @@ def test_transpose(self):
                          self.st_rich.data('2', 'observation'))
         self.assertEqual(obs.transpose(), self.st_rich)
 
+    def test_update_ids_strict_dtype_bug_issue_957(self):
+        t = Table(np.arange(6).reshape(2, 3),
+                  ['O1', 'O2'],
+                  ['ab', 'cdef', 'ghijkl'])
+        exp = Table(np.arange(6).reshape(2, 3),
+                    ['O1', 'O2'],
+                    ['AB', 'cdef', 'ghijkl'])
+        obs = t.update_ids({'ab': 'AB'}, strict=False, inplace=False)
+        self.assertEqual(obs, exp)
+
     def test_update_ids_inplace_bug_892(self):
         t = example_table.copy()
         exp = t.ids().copy()