From 3c720148eb9322f22255a872db4d2f713dc9cf6d Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Thu, 18 May 2023 16:29:53 -0400
Subject: [PATCH 01/22] group extension

---
 src/schema/rules/files/common/core.yaml   |  5 +--
 src/schema/rules/files/deriv/imaging.yaml | 12 +++----
 src/schema/rules/files/raw/anat.yaml      | 27 ++++++----------
 src/schema/rules/files/raw/dwi.yaml       |  6 ++--
 src/schema/rules/files/raw/eeg.yaml       |  5 +--
 src/schema/rules/files/raw/fmap.yaml      | 21 +++++--------
 src/schema/rules/files/raw/func.yaml      |  6 ++--
 src/schema/rules/files/raw/ieeg.yaml      |  8 ++---
 src/schema/rules/files/raw/meg.yaml       | 38 +++++++++++++++--------
 src/schema/rules/files/raw/micr.yaml      |  6 +---
 src/schema/rules/files/raw/perf.yaml      |  3 +-
 src/schema/rules/files/raw/pet.yaml       |  3 +-
 src/schema/rules/files/raw/photo.yaml     |  8 ++---
 13 files changed, 62 insertions(+), 86 deletions(-)

diff --git a/src/schema/rules/files/common/core.yaml b/src/schema/rules/files/common/core.yaml
index cacc3e0c41..54a37ca8e0 100644
--- a/src/schema/rules/files/common/core.yaml
+++ b/src/schema/rules/files/common/core.yaml
@@ -9,10 +9,7 @@ README:
   level: recommended
   stem: README
   extensions:
-    - ''
-    - .md
-    - .rst
-    - .txt
+    - ['', .md, .rst, .txt]
 CHANGES:
   level: optional
   path: CHANGES
diff --git a/src/schema/rules/files/deriv/imaging.yaml b/src/schema/rules/files/deriv/imaging.yaml
index e037dcc10c..d717c59ed0 100644
--- a/src/schema/rules/files/deriv/imaging.yaml
+++ b/src/schema/rules/files/deriv/imaging.yaml
@@ -94,8 +94,7 @@ anat_parametric_discrete_segmentation:
     density: optional
     description: optional
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
     - .tsv
 
@@ -110,8 +109,7 @@ anat_nonparametric_discrete_segmentation:
     density: optional
     description: optional
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
     - .tsv
 
@@ -190,8 +188,7 @@ anat_parametic_discrete_surface:
   suffixes:
     - dseg
   extensions:
-    - .label.gii
-    - .dlabel.nii
+    - [.label.gii, .dlabel.nii]
     - .json
     - .tsv
   entities:
@@ -207,8 +204,7 @@ anat_nonparametic_discrete_surface:
   suffixes:
     - dseg
   extensions:
-    - .label.gii
-    - .dlabel.nii
+    - [.label.gii, .dlabel.nii]
     - .json
     - .tsv
   entities:
diff --git a/src/schema/rules/files/raw/anat.yaml b/src/schema/rules/files/raw/anat.yaml
index 2e534a2817..c2c7159d60 100644
--- a/src/schema/rules/files/raw/anat.yaml
+++ b/src/schema/rules/files/raw/anat.yaml
@@ -14,8 +14,7 @@ nonparametric:
     - FLASH # deprecated
     - PD # deprecated
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -48,8 +47,7 @@ parametric:
     - S0map
     - M0map
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -66,8 +64,7 @@ defacemask:
   suffixes:
     - defacemask
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -86,8 +83,7 @@ multiecho:
     - MESE
     - MEGRE
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -106,8 +102,7 @@ multiflip:
   suffixes:
     - VFA
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -127,8 +122,7 @@ multiinversion:
   suffixes:
     - IRT1
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -147,8 +141,7 @@ mp2rage:
   suffixes:
     - MP2RAGE
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -170,8 +163,7 @@ vfamt:
     - MPM
     - MTS
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
@@ -192,8 +184,7 @@ mtr:
   suffixes:
     - MTR
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - anat
diff --git a/src/schema/rules/files/raw/dwi.yaml b/src/schema/rules/files/raw/dwi.yaml
index 98840ef6a1..ab36c60c8f 100644
--- a/src/schema/rules/files/raw/dwi.yaml
+++ b/src/schema/rules/files/raw/dwi.yaml
@@ -3,8 +3,7 @@ dwi:
   suffixes:
     - dwi
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
     - .bvec
     - .bval
@@ -23,8 +22,7 @@ sbref:
   suffixes:
     - sbref
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - dwi
diff --git a/src/schema/rules/files/raw/eeg.yaml b/src/schema/rules/files/raw/eeg.yaml
index 676d66dc1b..3262204536 100644
--- a/src/schema/rules/files/raw/eeg.yaml
+++ b/src/schema/rules/files/raw/eeg.yaml
@@ -4,13 +4,14 @@ eeg:
     - eeg
   extensions:
     - .json
-    - .edf
+    # .vhdr, .vmrk, .eeg must work as triplet
     - .vhdr
     - .vmrk
     - .eeg
+    # .set file with an OPTIONAL .fdt
     - .set
     - .fdt
-    - .bdf
+    - [.bdf, .edf]
   datatypes:
     - eeg
   entities:
diff --git a/src/schema/rules/files/raw/fmap.yaml b/src/schema/rules/files/raw/fmap.yaml
index 8f5e66a508..78a1c4d349 100644
--- a/src/schema/rules/files/raw/fmap.yaml
+++ b/src/schema/rules/files/raw/fmap.yaml
@@ -9,8 +9,7 @@ fieldmaps:
     - magnitude
     - fieldmap
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
@@ -25,8 +24,7 @@ pepolar:
     - epi
     - m0scan
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
@@ -42,8 +40,7 @@ TB1DAM:
   suffixes:
     - TB1DAM
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
@@ -62,8 +59,7 @@ TB1EPI:
   suffixes:
     - TB1EPI
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
@@ -86,8 +82,7 @@ RFFieldMaps:
     - TB1RFM
     - RB1COR
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
@@ -107,8 +102,7 @@ TB1SRGE:
   suffixes:
     - TB1SRGE
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
@@ -129,8 +123,7 @@ parametric:
     - TB1map
     - RB1map
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - fmap
diff --git a/src/schema/rules/files/raw/func.yaml b/src/schema/rules/files/raw/func.yaml
index 589d187444..11609e79e2 100644
--- a/src/schema/rules/files/raw/func.yaml
+++ b/src/schema/rules/files/raw/func.yaml
@@ -5,8 +5,7 @@ func:
     - cbv
     - sbref
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - func
@@ -26,8 +25,7 @@ phase:
   suffixes:
     - phase # deprecated
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - func
diff --git a/src/schema/rules/files/raw/ieeg.yaml b/src/schema/rules/files/raw/ieeg.yaml
index 587f9bcbb8..61b0a6a4b7 100644
--- a/src/schema/rules/files/raw/ieeg.yaml
+++ b/src/schema/rules/files/raw/ieeg.yaml
@@ -3,15 +3,15 @@ ieeg:
   suffixes:
     - ieeg
   extensions:
-    - .mefd/
     - .json
-    - .edf
+    # .vhdr, .vmrk, .eeg must work as triplet
     - .vhdr
-    - .eeg
     - .vmrk
+    - .eeg
+    # .set file with an OPTIONAL .fdt
     - .set
     - .fdt
-    - .nwb
+    - [.nwb, .edf, .mefd/]
   datatypes:
     - ieeg
   entities:
diff --git a/src/schema/rules/files/raw/meg.yaml b/src/schema/rules/files/raw/meg.yaml
index c308cd8b9b..50c321e0d8 100644
--- a/src/schema/rules/files/raw/meg.yaml
+++ b/src/schema/rules/files/raw/meg.yaml
@@ -3,19 +3,33 @@ meg:
   suffixes:
     - meg
   extensions:
-    - / # corresponds to BTi/4D data
-    - .ds/
+    # / corresponds to BTi/4D data
     - .json
-    - .fif
-    - .sqd
-    - .con
+    - [/, .ds/, .fif]
+    - [.sqd, .con]
+    - .ave # mentioned once in the appendix
     - .raw
-    - .ave
-    - .mrk
+    - .raw.mhd
+    # .kdf with possible additional files .chn, .trg and _digitizer.txt (see other suffix group below)
     - .kdf
-    - .mhd
-    - .trg
     - .chn
+    - .trg
+  datatypes:
+    - meg
+  entities:
+    subject: required
+    session: optional
+    task: required
+    acquisition: optional
+    run: optional
+    processing: optional
+    split: optional
+
+headpoints:
+  suffixes:
+    - digitizer
+  extensions:
+    - .txt
   datatypes:
     - meg
   entities:
@@ -61,8 +75,7 @@ headshape:
   suffixes:
     - headshape
   extensions:
-    - .*
-    - .pos
+    - [.*, .pos]
   datatypes:
     - meg
   entities:
@@ -74,8 +87,7 @@ markers:
   suffixes:
     - markers
   extensions:
-    - .sqd
-    - .mrk
+    - [.sqd, .mrk]
   datatypes:
     - meg
   entities:
diff --git a/src/schema/rules/files/raw/micr.yaml b/src/schema/rules/files/raw/micr.yaml
index aba1b48352..b8423f3b27 100644
--- a/src/schema/rules/files/raw/micr.yaml
+++ b/src/schema/rules/files/raw/micr.yaml
@@ -19,11 +19,7 @@ microscopy:
     - OCT
     - SPIM
   extensions:
-    - .ome.tif
-    - .ome.btf
-    - .ome.zarr/
-    - .png
-    - .tif
+    - [.ome.tif, .ome.btf, .ome.zarr/, .png, .tif]
     - .json
   datatypes:
     - micr
diff --git a/src/schema/rules/files/raw/perf.yaml b/src/schema/rules/files/raw/perf.yaml
index 61cbc24721..036f1f7969 100644
--- a/src/schema/rules/files/raw/perf.yaml
+++ b/src/schema/rules/files/raw/perf.yaml
@@ -4,8 +4,7 @@ asl:
     - asl
     - m0scan
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - perf
diff --git a/src/schema/rules/files/raw/pet.yaml b/src/schema/rules/files/raw/pet.yaml
index a94cb9addd..f88a9f78ce 100644
--- a/src/schema/rules/files/raw/pet.yaml
+++ b/src/schema/rules/files/raw/pet.yaml
@@ -3,8 +3,7 @@ pet:
   suffixes:
     - pet
   extensions:
-    - .nii.gz
-    - .nii
+    - [.nii.gz, .nii]
     - .json
   datatypes:
     - pet
diff --git a/src/schema/rules/files/raw/photo.yaml b/src/schema/rules/files/raw/photo.yaml
index f5969e2d0c..6529ed3c76 100644
--- a/src/schema/rules/files/raw/photo.yaml
+++ b/src/schema/rules/files/raw/photo.yaml
@@ -3,9 +3,7 @@ photo:
   suffixes:
     - photo
   extensions:
-    - .jpg
-    - .png
-    - .tif
+    - [.jpg, .png, .tif]
   datatypes:
     - eeg
     - ieeg
@@ -19,9 +17,7 @@ photo:
 photo__micr:
   $ref: rules.files.raw.photo.photo
   extensions:
-    - .jpg
-    - .png
-    - .tif
+    - [.jpg, .png, .tif]
     - .json
   datatypes:
     - micr

From 13eabdd33f082c2a29985fbed5f9a8d05f26e0dd Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Thu, 18 May 2023 16:30:52 -0400
Subject: [PATCH 02/22] add comment

---
 src/schema/rules/files/raw/meg.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/schema/rules/files/raw/meg.yaml b/src/schema/rules/files/raw/meg.yaml
index 50c321e0d8..d4ee878702 100644
--- a/src/schema/rules/files/raw/meg.yaml
+++ b/src/schema/rules/files/raw/meg.yaml
@@ -8,6 +8,7 @@ meg:
     - [/, .ds/, .fif]
     - [.sqd, .con]
     - .ave # mentioned once in the appendix
+    # .raw and .raw.mhd work as a pair
     - .raw
     - .raw.mhd
     # .kdf with possible additional files .chn, .trg and _digitizer.txt (see other suffix group below)

From d3594e7bcbc9f55ef91c5f9b7e80b0b14bd004f6 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Thu, 18 May 2023 16:44:02 -0400
Subject: [PATCH 03/22] put all extension for data in list

---
 src/schema/rules/files/raw/eeg.yaml  | 4 +---
 src/schema/rules/files/raw/ieeg.yaml | 4 +---
 src/schema/rules/files/raw/meg.yaml  | 5 +----
 3 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/src/schema/rules/files/raw/eeg.yaml b/src/schema/rules/files/raw/eeg.yaml
index 3262204536..396ce0835c 100644
--- a/src/schema/rules/files/raw/eeg.yaml
+++ b/src/schema/rules/files/raw/eeg.yaml
@@ -4,14 +4,12 @@ eeg:
     - eeg
   extensions:
     - .json
+    - [.bdf, .edf, .eeg, .set]
     # .vhdr, .vmrk, .eeg must work as triplet
     - .vhdr
     - .vmrk
-    - .eeg
     # .set file with an OPTIONAL .fdt
-    - .set
     - .fdt
-    - [.bdf, .edf]
   datatypes:
     - eeg
   entities:
diff --git a/src/schema/rules/files/raw/ieeg.yaml b/src/schema/rules/files/raw/ieeg.yaml
index 61b0a6a4b7..c267cf6d03 100644
--- a/src/schema/rules/files/raw/ieeg.yaml
+++ b/src/schema/rules/files/raw/ieeg.yaml
@@ -3,15 +3,13 @@ ieeg:
   suffixes:
     - ieeg
   extensions:
+    - [.nwb, .edf, .mefd/, .eeg, .set]
     - .json
     # .vhdr, .vmrk, .eeg must work as triplet
     - .vhdr
     - .vmrk
-    - .eeg
     # .set file with an OPTIONAL .fdt
-    - .set
     - .fdt
-    - [.nwb, .edf, .mefd/]
   datatypes:
     - ieeg
   entities:
diff --git a/src/schema/rules/files/raw/meg.yaml b/src/schema/rules/files/raw/meg.yaml
index d4ee878702..8198dd5c1d 100644
--- a/src/schema/rules/files/raw/meg.yaml
+++ b/src/schema/rules/files/raw/meg.yaml
@@ -5,14 +5,11 @@ meg:
   extensions:
     # / corresponds to BTi/4D data
     - .json
-    - [/, .ds/, .fif]
-    - [.sqd, .con]
+    - [/, .ds/, .fif, .sqd, .con, .raw, .kdf]
     - .ave # mentioned once in the appendix
     # .raw and .raw.mhd work as a pair
-    - .raw
     - .raw.mhd
     # .kdf with possible additional files .chn, .trg and _digitizer.txt (see other suffix group below)
-    - .kdf
     - .chn
     - .trg
   datatypes:

From b0d5dd53fc1e0a4af70f904dfb9819931a1fe6fd Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 15:02:18 -0400
Subject: [PATCH 04/22] rename some funtions

---
 tools/schemacode/bidsschematools/render/text.py    | 14 +++++++-------
 .../bidsschematools/tests/test_render_text.py      |  4 ++--
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index b43a33e617..4b9a1f5e31 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -54,14 +54,14 @@ def make_entity_definitions(schema, src_path=None):
     text = ""
     for entity in entity_order:
         entity_info = entity_definitions[entity]
-        entity_text = _make_entity_definition(entity, entity_info)
+        entity_text = _make_definition_for_entity(entity_info)
         text += "\n" + entity_text
 
     text = text.replace("SPEC_ROOT", utils.get_relpath(src_path))
     return text
 
 
-def _make_entity_definition(entity, entity_info):
+def _make_definition_for_entity(entity_info):
     """Describe an entity."""
     entity_shorthand = entity_info["name"]
     text = ""
@@ -208,7 +208,7 @@ def _format_entity(entity, lt, gt):
     return f"{entity['name']}-{lt}{fmt}{gt}"
 
 
-def value_key_table(namespace):
+def _value_key_table(namespace):
     return {struct.value: key for key, struct in namespace.items()}
 
 
@@ -272,8 +272,8 @@ def make_filename_template(
         lt, gt = "&lt;", "&gt;"
 
     schema = Namespace(filter_schema(schema.to_dict(), **kwargs))
-    suffix_key_table = value_key_table(schema.objects.suffixes)
-    ext_key_table = value_key_table(schema.objects.extensions)
+    suffix_key_table = _value_key_table(schema.objects.suffixes)
+    ext_key_table = _value_key_table(schema.objects.extensions)
 
     # Parent directories
     sub_string = utils._link_with_html(
@@ -411,13 +411,13 @@ def make_filename_template(
         )
 
     codeblock = codeblock.expandtabs(4)
-    codeblock = append_filename_template_legend(codeblock, pdf_format)
+    codeblock = _append_filename_template_legend(codeblock, pdf_format)
     codeblock = codeblock.replace("SPEC_ROOT", utils.get_relpath(src_path))
 
     return codeblock
 
 
-def append_filename_template_legend(text, pdf_format=False):
+def _append_filename_template_legend(text, pdf_format=False):
     """Append a legend to filename templates.
 
     Parameters
diff --git a/tools/schemacode/bidsschematools/tests/test_render_text.py b/tools/schemacode/bidsschematools/tests/test_render_text.py
index be9ceb132f..ed50e8ab78 100644
--- a/tools/schemacode/bidsschematools/tests/test_render_text.py
+++ b/tools/schemacode/bidsschematools/tests/test_render_text.py
@@ -117,11 +117,11 @@ def test_define_common_principles(schema_obj):
 
 def test_append_filename_template_legend():
     """Check contents of generated string."""
-    test_str = text.append_filename_template_legend("", pdf_format=False)
+    test_str = text._append_filename_template_legend("", pdf_format=False)
     assert isinstance(test_str, str)
     assert "follow the links" in test_str
 
-    test_str = text.append_filename_template_legend("", pdf_format=True)
+    test_str = text._append_filename_template_legend("", pdf_format=True)
     assert isinstance(test_str, str)
     assert "follow the links" not in test_str
 

From 160b9c5c8875d935621b2b371ce3e7c431950d5d Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 15:06:38 -0400
Subject: [PATCH 05/22] minor fixes

---
 src/appendices/meg-file-formats.md                         | 4 ++--
 src/schema/rules/files/raw/meg.yaml                        | 2 +-
 tools/schemacode/bidsschematools/render/text.py            | 7 ++++++-
 tools/schemacode/bidsschematools/render/utils.py           | 7 +++++++
 .../schemacode/bidsschematools/tests/test_render_utils.py  | 7 +++++++
 5 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/src/appendices/meg-file-formats.md b/src/appendices/meg-file-formats.md
index 0465b67472..eed5972e62 100644
--- a/src/appendices/meg-file-formats.md
+++ b/src/appendices/meg-file-formats.md
@@ -329,8 +329,8 @@ A guide for using macros can be found at
                 "sub-control01_ses-001_task-rest_run-01_meg": "",
                 "sub-control01_ses-001_task-rest_run-01_meg.json": "",
                 "sub-control01_ses-001_task-rest_run-01_channels.tsv": "",
-                "sub-control01_ses-001_task-rest[_acq-<label>]_run-01_markers.<mrk,sqd>": "",
-                "sub-control01_ses-001_task-rest_run-01_meg.<con,sqd>": "",
+                "sub-control01_ses-001_task-rest[_acq-<label>]_run-01_markers.<mrk|sqd>": "",
+                "sub-control01_ses-001_task-rest_run-01_meg.<con|sqd>": "",
                 },
             },
         },
diff --git a/src/schema/rules/files/raw/meg.yaml b/src/schema/rules/files/raw/meg.yaml
index 8198dd5c1d..4900438759 100644
--- a/src/schema/rules/files/raw/meg.yaml
+++ b/src/schema/rules/files/raw/meg.yaml
@@ -3,8 +3,8 @@ meg:
   suffixes:
     - meg
   extensions:
-    # / corresponds to BTi/4D data
     - .json
+    # / corresponds to BTi/4D data
     - [/, .ds/, .fif, .sqd, .con, .raw, .kdf]
     - .ave # mentioned once in the appendix
     # .raw and .raw.mhd work as a pair
diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 4b9a1f5e31..beef88aab6 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -370,7 +370,7 @@ def make_filename_template(
                 ]
 
             # Add extensions
-            extensions = [ext if ext != "*" else ".<extension>" for ext in group.extensions]
+            extensions = listify_all_extensions(group.extensions)
             if len(extensions) >= n_dupes_to_combine:
                 # Combine exts when there are many, but keep JSON separate
                 if ".json" in extensions:
@@ -417,6 +417,11 @@ def make_filename_template(
     return codeblock
 
 
+def listify_all_extensions(extensions) -> list[str]:
+    extensions = [ext if isinstance(ext, str) else ext[:] for ext in extensions]
+    return [ext if ext != "*" else ".<extension>" for ext in extensions]
+
+
 def _append_filename_template_legend(text, pdf_format=False):
     """Append a legend to filename templates.
 
diff --git a/tools/schemacode/bidsschematools/render/utils.py b/tools/schemacode/bidsschematools/render/utils.py
index 9764a4efbe..d2c72bdcd4 100644
--- a/tools/schemacode/bidsschematools/render/utils.py
+++ b/tools/schemacode/bidsschematools/render/utils.py
@@ -32,6 +32,13 @@ def _link_with_html(string, html_path=None, heading=None, pdf_format=False):
     return string
 
 
+def stringify_extension_group(lst, html_path=None, heading_lst=None, pdf_format=True):
+    tmp = combine_extensions(
+        lst, html_path=html_path, heading_lst=heading_lst, pdf_format=pdf_format
+    )
+    return f"<{'|'.join(tmp)}>"
+
+
 def combine_extensions(lst, html_path=None, heading_lst=None, pdf_format=True):
     """Combine extensions with their compressed versions in a list.
 
diff --git a/tools/schemacode/bidsschematools/tests/test_render_utils.py b/tools/schemacode/bidsschematools/tests/test_render_utils.py
index f669bdcb77..65d351e26c 100644
--- a/tools/schemacode/bidsschematools/tests/test_render_utils.py
+++ b/tools/schemacode/bidsschematools/tests/test_render_utils.py
@@ -1,6 +1,13 @@
 from bidsschematools.render import utils
 
 
+def test_stringify_extension_group():
+    test_extensions = ["bdf", "edf", "eeg", "set"]
+    target_string = "<bdf|edf|eeg|set>"
+    test_string = utils.stringify_extension_group(test_extensions, pdf_format=True)
+    assert test_string == target_string
+
+
 def test_combine_extensions():
     """A unit test for utils.combine_extensions."""
     test_extensions = ["nii.gz", "nii", "json"]

From 1eb0f636ff99fd5319bb5012a93c7790e8aeae59 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 16:23:06 -0400
Subject: [PATCH 06/22] fx rendering

---
 src/schema/objects/suffixes.yaml              |   4 +
 .../schemacode/bidsschematools/render/text.py | 154 +++++++++++-------
 .../bidsschematools/tests/test_render_text.py |  20 +++
 3 files changed, 120 insertions(+), 58 deletions(-)

diff --git a/src/schema/objects/suffixes.yaml b/src/schema/objects/suffixes.yaml
index 9d376864e2..bda1a46190 100644
--- a/src/schema/objects/suffixes.yaml
+++ b/src/schema/objects/suffixes.yaml
@@ -551,6 +551,10 @@ defacemask:
   description: |
     A binary mask that was used to remove facial features from an anatomical MRI
     image.
+digitizer:
+  value: digitizer
+  display_name: Digitizer
+  description: Digitized positions of the head points.
 dseg:
   value: dseg
   display_name: Discrete Segmentation
diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index beef88aab6..03f7cb9dda 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -272,8 +272,6 @@ def make_filename_template(
         lt, gt = "&lt;", "&gt;"
 
     schema = Namespace(filter_schema(schema.to_dict(), **kwargs))
-    suffix_key_table = _value_key_table(schema.objects.suffixes)
-    ext_key_table = _value_key_table(schema.objects.extensions)
 
     # Parent directories
     sub_string = utils._link_with_html(
@@ -299,7 +297,7 @@ def make_filename_template(
     for datatype in sorted(file_groups):
         datatype_string = utils._link_with_html(
             datatype,
-            html_path=GLOSSARY_PATH + ".html",
+            html_path=f"{GLOSSARY_PATH}.html",
             heading=f"{datatype.lower()}-datatypes",
             pdf_format=pdf_format,
         )
@@ -345,62 +343,35 @@ def make_filename_template(
 
                 ent_string = _add_entity(ent_string, pattern, entity["level"])
 
-            # In cases of large numbers of suffixes,
-            # we use the "suffix" variable and expect a table later in the spec
-            if len(group["suffixes"]) >= n_dupes_to_combine:
-                suffixes = [
-                    lt
-                    + utils._link_with_html(
-                        "suffix",
-                        html_path=GLOSSARY_PATH + ".html",
-                        heading="suffix-common_principles",
-                        pdf_format=pdf_format,
-                    )
-                    + gt
-                ]
-            else:
-                suffixes = [
-                    utils._link_with_html(
-                        suffix,
-                        html_path=GLOSSARY_PATH + ".html",
-                        heading=f"{suffix_key_table[suffix].lower()}-suffixes",
-                        pdf_format=pdf_format,
-                    )
-                    for suffix in group.suffixes
-                ]
-
-            # Add extensions
-            extensions = listify_all_extensions(group.extensions)
-            if len(extensions) >= n_dupes_to_combine:
-                # Combine exts when there are many, but keep JSON separate
-                if ".json" in extensions:
-                    extensions = [".<extension>", ".json"]
-                else:
-                    extensions = [".<extension>"]
-
-            ext_headings = []
-            for extension in extensions:
-                # The glossary indexes by the extension identifier (niigz instead of .nii.gz),
-                # but the rules reference the actual suffix string (.nii.gz instead of niigz),
-                # so we need to look it up.
-                key = ext_key_table.get(extension)
-                if key:
-                    ext_headings.append(f"{key.lower()}-extensions")
-                else:
-                    ext_headings.append("extension-common_principles")
+            suffixes = _suffixes_for_this_group(schema, group, n_dupes_to_combine, pdf_format)
 
-            extensions = utils.combine_extensions(
-                extensions,
-                html_path=GLOSSARY_PATH + ".html",
-                heading_lst=ext_headings,
-                pdf_format=pdf_format,
-            )
+            if _nb_extensions(group) >= n_dupes_to_combine or all(
+                isinstance(x, str) for x in group.extensions
+            ):
+                extensions = _listify_all_extensions(group.extensions)
 
-            lines.extend(
-                f"\t\t\t{ent_string}_{suffix}{extension}"
-                for suffix in sorted(suffixes)
-                for extension in sorted(extensions)
-            )
+                if _nb_extensions(group) >= n_dupes_to_combine:
+                    # Combine exts when there are many, but keep JSON separate
+                    if ".json" in extensions:
+                        extensions = [".<extension>", ".json"]
+                    else:
+                        extensions = [".<extension>"]
+
+                extensions = _combine_extensions_with_headings(schema, extensions, pdf_format)
+                lines.extend(
+                    f"\t\t\t{ent_string}_{suffix}{extension}"
+                    for suffix in sorted(suffixes)
+                    for extension in sorted(extensions)
+                )
+
+            else:
+                for i in group.extensions:
+                    extensions = _combine_extensions_with_headings(schema, i, pdf_format)
+                    lines.extend(
+                        f"\t\t\t{ent_string}_{suffix}{extension}"
+                        for suffix in sorted(suffixes)
+                        for extension in sorted(extensions)
+                    )
 
     paragraph = "\n".join(lines)
     if pdf_format:
@@ -417,7 +388,74 @@ def make_filename_template(
     return codeblock
 
 
-def listify_all_extensions(extensions) -> list[str]:
+def _suffixes_for_this_group(
+    schema, group, n_dupes_to_combine: int, pdf_format: bool
+) -> list[str]:
+    suffix_key_table = _value_key_table(schema.objects.suffixes)
+
+    lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
+
+    # In cases of large numbers of suffixes,
+    # we use the "suffix" variable and expect a table later in the spec
+    if len(group["suffixes"]) >= n_dupes_to_combine:
+        suffixes = [
+            lt
+            + utils._link_with_html(
+                "suffix",
+                html_path=f"{GLOSSARY_PATH}.html",
+                heading="suffix-common_principles",
+                pdf_format=pdf_format,
+            )
+            + gt
+        ]
+
+        return suffixes
+
+    return [
+        utils._link_with_html(
+            suffix,
+            html_path=f"{GLOSSARY_PATH}.html",
+            heading=f"{suffix_key_table[suffix].lower()}-suffixes",
+            pdf_format=pdf_format,
+        )
+        for suffix in group.suffixes
+    ]
+
+
+def _combine_extensions_with_headings(schema, extensions: str | list[str], pdf_format: bool):
+    if isinstance(extensions, str):
+        extensions = [extensions]
+
+    ext_headings = _get_extension_headings(schema, extensions)
+
+    return utils.combine_extensions(
+        extensions,
+        html_path=f"{GLOSSARY_PATH}.html",
+        heading_lst=ext_headings,
+        pdf_format=pdf_format,
+    )
+
+
+def _get_extension_headings(schema, extensions):
+    """The glossary indexes by the extension identifier (niigz instead of .nii.gz),
+    but the rules reference the actual suffix string (.nii.gz instead of niigz),
+    so we need to look it up."""
+    ext_key_table = _value_key_table(schema.objects.extensions)
+    ext_headings = []
+    for extension in extensions:
+        key = ext_key_table.get(extension)
+        if key:
+            ext_headings.append(f"{key.lower()}-extensions")
+        else:
+            ext_headings.append("extension-common_principles")
+    return ext_headings
+
+
+def _nb_extensions(group):
+    return len(_listify_all_extensions(group))
+
+
+def _listify_all_extensions(extensions) -> list[str]:
     extensions = [ext if isinstance(ext, str) else ext[:] for ext in extensions]
     return [ext if ext != "*" else ".<extension>" for ext in extensions]
 
diff --git a/tools/schemacode/bidsschematools/tests/test_render_text.py b/tools/schemacode/bidsschematools/tests/test_render_text.py
index ed50e8ab78..d4338cf69c 100644
--- a/tools/schemacode/bidsschematools/tests/test_render_text.py
+++ b/tools/schemacode/bidsschematools/tests/test_render_text.py
@@ -1,6 +1,8 @@
 """Tests for the bidsschematools package."""
 import os
 
+import pytest
+
 from bidsschematools.render import text
 
 
@@ -130,3 +132,21 @@ def test_define_allowed_top_directories(schema_obj):
     """smoke test for allowed top directories."""
     test_str = text.define_allowed_top_directories(schema_obj)
     assert isinstance(test_str, str)
+
+
+@pytest.mark.parametrize(
+    "extensions, expected, pdf_format",
+    [
+        (
+            ["json"],
+            ['<a href="SPEC_ROOT/glossary.html#extension-common_principles">json</a>'],
+            False,
+        ),
+        (["nii.gz", "nii", "json"], ["nii[.gz]", "json"], True),
+    ],
+)
+def test_extension_for_this_group(schema_obj, extensions, expected, pdf_format):
+    extensions = text._combine_extensions_with_headings(
+        schema_obj, extensions, pdf_format=pdf_format
+    )
+    assert extensions == expected

From bcf5ebc2e51578710b29cf58c5a08592c27a349f Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 16:43:02 -0400
Subject: [PATCH 07/22] attempt at fixing rules

---
 tools/schemacode/bidsschematools/rules.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/schemacode/bidsschematools/rules.py b/tools/schemacode/bidsschematools/rules.py
index 301dc13f1b..29bf5cb164 100644
--- a/tools/schemacode/bidsschematools/rules.py
+++ b/tools/schemacode/bidsschematools/rules.py
@@ -162,7 +162,11 @@ def _sanitize_extension(ext: str) -> str:
 
 def _stem_rule(rule: bst.types.Namespace):
     stem_regex = re.escape(rule.stem)
-    ext_match = "|".join(_sanitize_extension(ext) for ext in rule.extensions)
+    if isinstance(rule.extensions[0], list) and len(rule.extensions) == 1:
+        extensions = rule.extensions[0]
+    else:
+        extensions = rule.extensions
+    ext_match = "|".join(_sanitize_extension(ext) for ext in extensions)
     ext_regex = f"(?P<extension>{ext_match})"
 
     return {"regex": stem_regex + ext_regex, "mandatory": rule.level == "required"}

From 9708eb39d20402a57a1a106d77e8a2636cc6bf4b Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 18:48:22 -0400
Subject: [PATCH 08/22] properly combine extensions

---
 .../magnetoencephalography.md                 |  2 +-
 .../schemacode/bidsschematools/render/text.py | 46 +++++++++++---
 .../bidsschematools/render/utils.py           |  7 ---
 .../bidsschematools/tests/test_render_text.py | 60 +++++++++++++++++--
 .../tests/test_render_utils.py                |  7 ---
 5 files changed, 93 insertions(+), 29 deletions(-)

diff --git a/src/modality-specific-files/magnetoencephalography.md b/src/modality-specific-files/magnetoencephalography.md
index 6f0b4c0baa..fc42d318db 100644
--- a/src/modality-specific-files/magnetoencephalography.md
+++ b/src/modality-specific-files/magnetoencephalography.md
@@ -26,7 +26,7 @@ and a guide for using macros can be found at
 {{ MACROS___make_filename_template(
    "raw",
    datatypes=["meg"],
-   suffixes=["meg", "markers", "events", "physio", "stim"])
+   suffixes=["meg", "markers", "events", "physio", "stim", "digitizer"])
 }}
 
 Unprocessed MEG data MUST be stored in the native file format of the MEG
diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 03f7cb9dda..1293a2086e 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -218,6 +218,7 @@ def make_filename_template(
     src_path=None,
     n_dupes_to_combine=6,
     pdf_format=False,
+    include_legend=True,
     **kwargs,
 ):
     """Create codeblocks containing example filename patterns for a given datatype.
@@ -230,15 +231,19 @@ def make_filename_template(
     dstype : "raw" or "deriv"
         The type of files being rendered; determines if rules are found in rules.files.raw
         or rules.files.deriv
+
     schema : dict
         The schema object, which is a dictionary with nested dictionaries and
         lists stored within it.
+
     src_path : str or None
         The file where this macro is called, which may be explicitly provided
         by the "page.file.src_path" variable.
+
     n_dupes_to_combine : int
         The minimum number of suffixes/extensions to combine in the template as
         <suffix>/<extension>.
+
     pdf_format : bool, optional
         If True, the filename template will be compiled as a standard markdown code block,
         without any hyperlinks, so that the specification's PDF build will look right.
@@ -246,6 +251,9 @@ def make_filename_template(
         This works on the website.
         Default is False.
 
+    include_legend : bool, optional
+        If True, the filename template will include a legend below the codeblock.
+
     Other Parameters
     ----------------
     **kwargs : dict
@@ -358,6 +366,7 @@ def make_filename_template(
                         extensions = [".<extension>"]
 
                 extensions = _combine_extensions_with_headings(schema, extensions, pdf_format)
+
                 lines.extend(
                     f"\t\t\t{ent_string}_{suffix}{extension}"
                     for suffix in sorted(suffixes)
@@ -365,8 +374,17 @@ def make_filename_template(
                 )
 
             else:
-                for i in group.extensions:
-                    extensions = _combine_extensions_with_headings(schema, i, pdf_format)
+                for extension_ in group.extensions:
+                    if isinstance(extension_, str):
+                        extensions = _combine_extensions_with_headings(
+                            schema, extension_, pdf_format
+                        )
+                    elif isinstance(extension_, list):
+                        extensions = _combine_extensions_with_headings(
+                            schema, extension_, pdf_format, mutually_exclusive=True
+                        )
+                        extensions = [extensions]
+
                     lines.extend(
                         f"\t\t\t{ent_string}_{suffix}{extension}"
                         for suffix in sorted(suffixes)
@@ -382,7 +400,8 @@ def make_filename_template(
         )
 
     codeblock = codeblock.expandtabs(4)
-    codeblock = _append_filename_template_legend(codeblock, pdf_format)
+    if include_legend:
+        codeblock = _append_filename_template_legend(codeblock, pdf_format)
     codeblock = codeblock.replace("SPEC_ROOT", utils.get_relpath(src_path))
 
     return codeblock
@@ -422,19 +441,23 @@ def _suffixes_for_this_group(
     ]
 
 
-def _combine_extensions_with_headings(schema, extensions: str | list[str], pdf_format: bool):
+def _combine_extensions_with_headings(
+    schema, extensions: str | list[str], pdf_format: bool, mutually_exclusive: bool = False
+):
     if isinstance(extensions, str):
         extensions = [extensions]
 
     ext_headings = _get_extension_headings(schema, extensions)
 
-    return utils.combine_extensions(
+    extensions = utils.combine_extensions(
         extensions,
         html_path=f"{GLOSSARY_PATH}.html",
         heading_lst=ext_headings,
         pdf_format=pdf_format,
     )
 
+    return f"<{'|'.join(extensions)}>" if mutually_exclusive else extensions
+
 
 def _get_extension_headings(schema, extensions):
     """The glossary indexes by the extension identifier (niigz instead of .nii.gz),
@@ -452,12 +475,17 @@ def _get_extension_headings(schema, extensions):
 
 
 def _nb_extensions(group):
-    return len(_listify_all_extensions(group))
+    return len(_listify_all_extensions(group.extensions))
 
 
-def _listify_all_extensions(extensions) -> list[str]:
-    extensions = [ext if isinstance(ext, str) else ext[:] for ext in extensions]
-    return [ext if ext != "*" else ".<extension>" for ext in extensions]
+def _listify_all_extensions(extensions: list[str | list[str]]) -> list[str]:
+    tmp = []
+    for ext in extensions:
+        if isinstance(ext, str):
+            tmp.append(ext)
+        else:
+            tmp.extend(ext)
+    return [ext if ext != "*" else ".<extension>" for ext in tmp]
 
 
 def _append_filename_template_legend(text, pdf_format=False):
diff --git a/tools/schemacode/bidsschematools/render/utils.py b/tools/schemacode/bidsschematools/render/utils.py
index d2c72bdcd4..9764a4efbe 100644
--- a/tools/schemacode/bidsschematools/render/utils.py
+++ b/tools/schemacode/bidsschematools/render/utils.py
@@ -32,13 +32,6 @@ def _link_with_html(string, html_path=None, heading=None, pdf_format=False):
     return string
 
 
-def stringify_extension_group(lst, html_path=None, heading_lst=None, pdf_format=True):
-    tmp = combine_extensions(
-        lst, html_path=html_path, heading_lst=heading_lst, pdf_format=pdf_format
-    )
-    return f"<{'|'.join(tmp)}>"
-
-
 def combine_extensions(lst, html_path=None, heading_lst=None, pdf_format=True):
     """Combine extensions with their compressed versions in a list.
 
diff --git a/tools/schemacode/bidsschematools/tests/test_render_text.py b/tools/schemacode/bidsschematools/tests/test_render_text.py
index d4338cf69c..91381d6fec 100644
--- a/tools/schemacode/bidsschematools/tests/test_render_text.py
+++ b/tools/schemacode/bidsschematools/tests/test_render_text.py
@@ -42,13 +42,13 @@ def test_make_glossary(schema_obj, schema_dir):
     """
     # Test consistency
     object_files = []
-    for root, dirs, files in os.walk(schema_dir, topdown=False):
+    for root, _, files in os.walk(schema_dir, topdown=False):
         if "objects" in root:
             for object_file in files:
                 object_base, _ = os.path.splitext(object_file)
                 object_files.append(object_base)
     rule_files = []
-    for root, dirs, files in os.walk(schema_dir, topdown=False):
+    for root, _, files in os.walk(schema_dir, topdown=False):
         if "rules" in root:
             for rule_file in files:
                 rule_base, _ = os.path.splitext(rule_file)
@@ -59,12 +59,12 @@ def test_make_glossary(schema_obj, schema_dir):
     for line in glossary.split("\n"):
         if line.startswith('<a name="objects.'):
             # Are all objects objects?
-            assert any([line.startswith(f'<a name="objects.{i}') for i in object_files])
+            assert any(line.startswith(f'<a name="objects.{i}') for i in object_files)
             # Are rules loaded incorrectly?
-            assert not any([line.startswith(f'<a name="objects.{i}') for i in rules_only])
+            assert not any(line.startswith(f'<a name="objects.{i}') for i in rules_only)
 
 
-def test_make_filename_template(schema_obj, schema_dir):
+def test_make_filename_template(schema_obj):
     """
     Test whether:
         * the base hierarchy structure of mandatory subject and optional session is
@@ -108,6 +108,38 @@ def test_make_filename_template(schema_obj, schema_dir):
     assert datatype_bases_found == datatype_count
 
 
+def test_make_filename_template_mutually_exclusive_extensions():
+    """Extensions that are mutually exclusive appear on a single line.
+
+    In this case mrk and sqd for MEG data.
+    """
+    filename_template = text.make_filename_template(
+        "raw",
+        datatypes=["meg"],
+        suffixes=["markers"],
+        pdf_format=True,
+        include_legend=False,
+    )
+    print(filename_template)
+    assert "legend" not in filename_template
+    nb_lines = len(filename_template.split("\n"))
+    assert nb_lines == 7
+
+
+def test_make_filename_template_mutually_combine_extensions_when_too_many():
+    """Combine extensions on a single line, there are too many extensions."""
+    filename_template = text.make_filename_template(
+        "raw",
+        datatypes=["meg"],
+        suffixes=["meg"],
+        pdf_format=True,
+        include_legend=False,
+    )
+    print(filename_template)
+    nb_lines = len(filename_template.split("\n"))
+    assert nb_lines == 10
+
+
 def test_define_common_principles(schema_obj):
     """Ensure that define_common_principles returns a string."""
     common_principles_str = text.define_common_principles(schema_obj)
@@ -150,3 +182,21 @@ def test_extension_for_this_group(schema_obj, extensions, expected, pdf_format):
         schema_obj, extensions, pdf_format=pdf_format
     )
     assert extensions == expected
+
+
+class Group:
+    def __init__(self, extensions):
+        self.extensions = extensions
+
+
+@pytest.mark.parametrize("extensions, expected", [(["nii"], 1), (["nii", ["bar", "baz"]], 3)])
+def test_nb_extensions(extensions, expected):
+    group = Group(extensions=extensions)
+    assert text._nb_extensions(group) == expected
+
+
+@pytest.mark.parametrize(
+    "extensions, expected", [(["nii"], ["nii"]), (["nii", ["bar", "baz"]], ["nii", "bar", "baz"])]
+)
+def test_listify_all_extensions(extensions, expected):
+    assert text._listify_all_extensions(extensions) == expected
diff --git a/tools/schemacode/bidsschematools/tests/test_render_utils.py b/tools/schemacode/bidsschematools/tests/test_render_utils.py
index 65d351e26c..f669bdcb77 100644
--- a/tools/schemacode/bidsschematools/tests/test_render_utils.py
+++ b/tools/schemacode/bidsschematools/tests/test_render_utils.py
@@ -1,13 +1,6 @@
 from bidsschematools.render import utils
 
 
-def test_stringify_extension_group():
-    test_extensions = ["bdf", "edf", "eeg", "set"]
-    target_string = "<bdf|edf|eeg|set>"
-    test_string = utils.stringify_extension_group(test_extensions, pdf_format=True)
-    assert test_string == target_string
-
-
 def test_combine_extensions():
     """A unit test for utils.combine_extensions."""
     test_extensions = ["nii.gz", "nii", "json"]

From e4b292218c070527a25fd812870a166c9d3b0276 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 19:20:57 -0400
Subject: [PATCH 09/22] add doc

---
 .../schemacode/bidsschematools/render/text.py | 84 +++++++++++++------
 1 file changed, 57 insertions(+), 27 deletions(-)

diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 1293a2086e..553815c565 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -274,23 +274,20 @@ def make_filename_template(
     if not schema:
         schema = load_schema()
 
-    if pdf_format:
-        lt, gt = "<", ">"
-    else:
-        lt, gt = "&lt;", "&gt;"
+    lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
 
     schema = Namespace(filter_schema(schema.to_dict(), **kwargs))
 
     # Parent directories
     sub_string = utils._link_with_html(
         _format_entity(schema.objects.entities.subject, lt, gt),
-        html_path=ENTITIES_PATH + ".html",
+        html_path=f"{ENTITIES_PATH}.html",
         heading="sub",
         pdf_format=pdf_format,
     )
     ses_string = utils._link_with_html(
         _format_entity(schema.objects.entities.session, lt, gt),
-        html_path=ENTITIES_PATH + ".html",
+        html_path=f"{ENTITIES_PATH}.html",
         heading="ses",
         pdf_format=pdf_format,
     )
@@ -353,6 +350,11 @@ def make_filename_template(
 
             suffixes = _suffixes_for_this_group(schema, group, n_dupes_to_combine, pdf_format)
 
+            # Deal with extensions for this suffix group
+            # 1) Either we have many extensions,
+            # in this case we combine them into a single extension
+            # or we have only non mutually exclusive extensions
+            # in this case we keep them separate on separate lines
             if _nb_extensions(group) >= n_dupes_to_combine or all(
                 isinstance(x, str) for x in group.extensions
             ):
@@ -373,6 +375,8 @@ def make_filename_template(
                     for extension in sorted(extensions)
                 )
 
+            # 2) We have some mutually exclusive extensions in this suffix group
+            # in this case those extensions are combined onto a single line
             else:
                 for extension_ in group.extensions:
                     if isinstance(extension_, str):
@@ -410,13 +414,23 @@ def make_filename_template(
 def _suffixes_for_this_group(
     schema, group, n_dupes_to_combine: int, pdf_format: bool
 ) -> list[str]:
-    suffix_key_table = _value_key_table(schema.objects.suffixes)
+    """List all suffixes in the template with their headings in the glossary \
+       if necessary.
 
-    lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
+    In cases of large numbers of suffixes,
+    we use the "suffix" variable and expect a table later in the spec.
+
+    Parameters
+    ----------
+    group :
+        A group of suffixes in the schema.
+
+    See make_filename_template for parameters description.
+    """
 
-    # In cases of large numbers of suffixes,
-    # we use the "suffix" variable and expect a table later in the spec
     if len(group["suffixes"]) >= n_dupes_to_combine:
+        lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
+
         suffixes = [
             lt
             + utils._link_with_html(
@@ -430,20 +444,32 @@ def _suffixes_for_this_group(
 
         return suffixes
 
-    return [
-        utils._link_with_html(
-            suffix,
-            html_path=f"{GLOSSARY_PATH}.html",
-            heading=f"{suffix_key_table[suffix].lower()}-suffixes",
-            pdf_format=pdf_format,
-        )
-        for suffix in group.suffixes
-    ]
+    else:
+        suffix_key_table = _value_key_table(schema.objects.suffixes)
+
+        return [
+            utils._link_with_html(
+                suffix,
+                html_path=f"{GLOSSARY_PATH}.html",
+                heading=f"{suffix_key_table[suffix].lower()}-suffixes",
+                pdf_format=pdf_format,
+            )
+            for suffix in group.suffixes
+        ]
 
 
 def _combine_extensions_with_headings(
     schema, extensions: str | list[str], pdf_format: bool, mutually_exclusive: bool = False
-):
+) -> str | list[str]:
+    """
+    Parameters
+    ----------
+    mutually_exclusive : bool, default=False
+        Set to True if the extensions are mutually exclusive (e.g. .nii and .nii.gz)
+        when you cannot have 2 data files that only differ by extension.
+
+    See make_filename_template for other parameters description.
+    """
     if isinstance(extensions, str):
         extensions = [extensions]
 
@@ -456,10 +482,12 @@ def _combine_extensions_with_headings(
         pdf_format=pdf_format,
     )
 
-    return f"<{'|'.join(extensions)}>" if mutually_exclusive else extensions
+    lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
+
+    return f"{lt}{'|'.join(extensions)}{gt}" if mutually_exclusive else extensions
 
 
-def _get_extension_headings(schema, extensions):
+def _get_extension_headings(schema, extensions: list[str]) -> list[str]:
     """The glossary indexes by the extension identifier (niigz instead of .nii.gz),
     but the rules reference the actual suffix string (.nii.gz instead of niigz),
     so we need to look it up."""
@@ -474,7 +502,7 @@ def _get_extension_headings(schema, extensions):
     return ext_headings
 
 
-def _nb_extensions(group):
+def _nb_extensions(group) -> int:
     return len(_listify_all_extensions(group.extensions))
 
 
@@ -488,7 +516,7 @@ def _listify_all_extensions(extensions: list[str | list[str]]) -> list[str]:
     return [ext if ext != "*" else ".<extension>" for ext in tmp]
 
 
-def _append_filename_template_legend(text, pdf_format=False):
+def _append_filename_template_legend(text: str, pdf_format=False) -> str:
     """Append a legend to filename templates.
 
     Parameters
@@ -542,13 +570,14 @@ def _append_filename_template_legend(text, pdf_format=False):
     return text
 
 
-def define_common_principles(schema, src_path=None):
+def define_common_principles(schema, src_path: str | None = None) -> str:
     """Enumerate the common principles defined in the schema.
 
     Parameters
     ----------
-    schema : dict
+    schema :
         The BIDS schema.
+
     src_path : str or None
         The file where this macro is called, which may be explicitly provided
         by the "page.file.src_path" variable.
@@ -575,13 +604,14 @@ def define_common_principles(schema, src_path=None):
     return string
 
 
-def define_allowed_top_directories(schema, src_path=None) -> str:
+def define_allowed_top_directories(schema, src_path: str | None = None) -> str:
     """Create a list of allowed top-level directories with their descriptions.
 
     Parameters
     ----------
     schema : dict
         The BIDS schema.
+
     src_path : str or None
         The file where this macro is called, which may be explicitly provided
         by the "page.file.src_path" variable.

From f28d3c2bf067847fe47872596c416c0814e4f024 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 19:24:32 -0400
Subject: [PATCH 10/22] import annotation for backward compatibility

---
 tools/schemacode/bidsschematools/render/text.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 553815c565..5f0cb9fed1 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -1,4 +1,7 @@
 """Functions for rendering portions of the schema as text."""
+
+from __future__ import annotations
+
 import logging
 import os
 

From cd1da9d80ad7b9c0532e2bccf6407941afda2101 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Sat, 20 May 2023 19:30:48 -0400
Subject: [PATCH 11/22] add type hints

---
 tools/schemacode/bidsschematools/render/text.py | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 5f0cb9fed1..8eac87bc7b 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -415,7 +415,7 @@ def make_filename_template(
 
 
 def _suffixes_for_this_group(
-    schema, group, n_dupes_to_combine: int, pdf_format: bool
+    schema: Namespace, group, n_dupes_to_combine: int, pdf_format: bool
 ) -> list[str]:
     """List all suffixes in the template with their headings in the glossary \
        if necessary.
@@ -462,7 +462,10 @@ def _suffixes_for_this_group(
 
 
 def _combine_extensions_with_headings(
-    schema, extensions: str | list[str], pdf_format: bool, mutually_exclusive: bool = False
+    schema: Namespace,
+    extensions: str | list[str],
+    pdf_format: bool,
+    mutually_exclusive: bool = False,
 ) -> str | list[str]:
     """
     Parameters
@@ -490,7 +493,7 @@ def _combine_extensions_with_headings(
     return f"{lt}{'|'.join(extensions)}{gt}" if mutually_exclusive else extensions
 
 
-def _get_extension_headings(schema, extensions: list[str]) -> list[str]:
+def _get_extension_headings(schema: Namespace, extensions: list[str]) -> list[str]:
     """The glossary indexes by the extension identifier (niigz instead of .nii.gz),
     but the rules reference the actual suffix string (.nii.gz instead of niigz),
     so we need to look it up."""
@@ -573,7 +576,7 @@ def _append_filename_template_legend(text: str, pdf_format=False) -> str:
     return text
 
 
-def define_common_principles(schema, src_path: str | None = None) -> str:
+def define_common_principles(schema: Namespace, src_path: str | None = None) -> str:
     """Enumerate the common principles defined in the schema.
 
     Parameters
@@ -607,7 +610,7 @@ def define_common_principles(schema, src_path: str | None = None) -> str:
     return string
 
 
-def define_allowed_top_directories(schema, src_path: str | None = None) -> str:
+def define_allowed_top_directories(schema: Namespace, src_path: str | None = None) -> str:
     """Create a list of allowed top-level directories with their descriptions.
 
     Parameters

From 341f7ae53b4b53dd68d926cb10b2b17c0daed1a5 Mon Sep 17 00:00:00 2001
From: Chris Markiewicz <effigies@gmail.com>
Date: Mon, 29 May 2023 07:57:45 -0400
Subject: [PATCH 12/22] RF: Fix extension list combination, remove some
 indirection

---
 .../schemacode/bidsschematools/render/text.py | 209 +++++-------------
 1 file changed, 57 insertions(+), 152 deletions(-)

diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 9197a56b9d..81e63719ef 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -57,14 +57,14 @@ def make_entity_definitions(schema, src_path=None):
     text = ""
     for entity in entity_order:
         entity_info = entity_definitions[entity]
-        entity_text = _make_definition_for_entity(entity_info)
+        entity_text = _make_entity_definition(entity_info)
         text += "\n" + entity_text
 
     text = text.replace("SPEC_ROOT", utils.get_relpath(src_path))
     return text
 
 
-def _make_definition_for_entity(entity_info):
+def _make_entity_definition(entity_info):
     """Describe an entity."""
     entity_shorthand = entity_info["name"]
     text = ""
@@ -211,7 +211,7 @@ def _format_entity(entity, lt, gt):
     return f"{entity['name']}-{lt}{fmt}{gt}"
 
 
-def _value_key_table(namespace):
+def value_key_table(namespace):
     return {struct.value: key for key, struct in namespace.items()}
 
 
@@ -280,6 +280,8 @@ def make_filename_template(
     lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
 
     schema = Namespace(filter_schema(schema.to_dict(), **kwargs))
+    suffix_key_table = value_key_table(schema.objects.suffixes)
+    ext_key_table = value_key_table(schema.objects.extensions)
 
     # Parent directories
     sub_string = utils._link_with_html(
@@ -351,53 +353,64 @@ def make_filename_template(
 
                 ent_string = _add_entity(ent_string, pattern, entity["level"])
 
-            suffixes = _suffixes_for_this_group(schema, group, n_dupes_to_combine, pdf_format)
-
-            # Deal with extensions for this suffix group
-            # 1) Either we have many extensions,
-            # in this case we combine them into a single extension
-            # or we have only non mutually exclusive extensions
-            # in this case we keep them separate on separate lines
-            if _nb_extensions(group) >= n_dupes_to_combine or all(
-                isinstance(x, str) for x in group.extensions
-            ):
-                extensions = _listify_all_extensions(group.extensions)
-
-                if _nb_extensions(group) >= n_dupes_to_combine:
-                    # Combine exts when there are many, but keep JSON separate
-                    if ".json" in extensions:
-                        extensions = [".<extension>", ".json"]
+            # In cases of large numbers of suffixes,
+            # we use the "suffix" variable and expect a table later in the spec
+            if len(group["suffixes"]) >= n_dupes_to_combine:
+                suffixes = [
+                    lt
+                    + utils._link_with_html(
+                        "suffix",
+                        html_path=GLOSSARY_PATH + ".html",
+                        heading="suffix-common_principles",
+                        pdf_format=pdf_format,
+                    )
+                    + gt
+                ]
+            else:
+                suffixes = [
+                    utils._link_with_html(
+                        suffix,
+                        html_path=GLOSSARY_PATH + ".html",
+                        heading=f"{suffix_key_table[suffix].lower()}-suffixes",
+                        pdf_format=pdf_format,
+                    )
+                    for suffix in group.suffixes
+                ]
+
+            # Add extensions
+            extension_groups = [
+                [".<extension>" if ext == "*" else ext]
+                if isinstance(ext, str)
+                else ([".<extension>"] if len(ext) >= n_dupes_to_combine else ext)
+                for ext in group.extensions
+            ]
+            for ext_group in sorted(extension_groups):
+                ext_headings = []
+                for extension in ext_group:
+                    # The glossary indexes by the extension identifier (niigz instead of .nii.gz),
+                    # but the rules reference the actual suffix string (.nii.gz instead of niigz),
+                    # so we need to look it up.
+                    key = ext_key_table.get(extension)
+                    if key:
+                        ext_headings.append(f"{key.lower()}-extensions")
                     else:
-                        extensions = [".<extension>"]
+                        ext_headings.append("extension-common_principles")
 
-                extensions = _combine_extensions_with_headings(schema, extensions, pdf_format)
+                extensions = utils.combine_extensions(
+                    ext_group,
+                    html_path=GLOSSARY_PATH + ".html",
+                    heading_lst=ext_headings,
+                    pdf_format=pdf_format,
+                )
+                if len(extensions) == 1:
+                    extension = extensions[0]
+                else:
+                    extension = f"{lt}{'|'.join(extensions)}{gt}"
 
                 lines.extend(
-                    f"\t\t\t{ent_string}_{suffix}{extension}"
-                    for suffix in sorted(suffixes)
-                    for extension in sorted(extensions)
+                    f"\t\t\t{ent_string}_{suffix}{extension}" for suffix in sorted(suffixes)
                 )
 
-            # 2) We have some mutually exclusive extensions in this suffix group
-            # in this case those extensions are combined onto a single line
-            else:
-                for extension_ in group.extensions:
-                    if isinstance(extension_, str):
-                        extensions = _combine_extensions_with_headings(
-                            schema, extension_, pdf_format
-                        )
-                    elif isinstance(extension_, list):
-                        extensions = _combine_extensions_with_headings(
-                            schema, extension_, pdf_format, mutually_exclusive=True
-                        )
-                        extensions = [extensions]
-
-                    lines.extend(
-                        f"\t\t\t{ent_string}_{suffix}{extension}"
-                        for suffix in sorted(suffixes)
-                        for extension in sorted(extensions)
-                    )
-
     paragraph = "\n".join(lines)
     if pdf_format:
         codeblock = f"Template:\n```Text\n{paragraph}\n```"
@@ -414,114 +427,6 @@ def make_filename_template(
     return codeblock
 
 
-def _suffixes_for_this_group(
-    schema: Namespace, group, n_dupes_to_combine: int, pdf_format: bool
-) -> list[str]:
-    """List all suffixes in the template with their headings in the glossary \
-       if necessary.
-
-    In cases of large numbers of suffixes,
-    we use the "suffix" variable and expect a table later in the spec.
-
-    Parameters
-    ----------
-    group :
-        A group of suffixes in the schema.
-
-    See make_filename_template for parameters description.
-    """
-
-    if len(group["suffixes"]) >= n_dupes_to_combine:
-        lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
-
-        suffixes = [
-            lt
-            + utils._link_with_html(
-                "suffix",
-                html_path=f"{GLOSSARY_PATH}.html",
-                heading="suffix-common_principles",
-                pdf_format=pdf_format,
-            )
-            + gt
-        ]
-
-        return suffixes
-
-    else:
-        suffix_key_table = _value_key_table(schema.objects.suffixes)
-
-        return [
-            utils._link_with_html(
-                suffix,
-                html_path=f"{GLOSSARY_PATH}.html",
-                heading=f"{suffix_key_table[suffix].lower()}-suffixes",
-                pdf_format=pdf_format,
-            )
-            for suffix in group.suffixes
-        ]
-
-
-def _combine_extensions_with_headings(
-    schema: Namespace,
-    extensions: str | list[str],
-    pdf_format: bool,
-    mutually_exclusive: bool = False,
-) -> str | list[str]:
-    """
-    Parameters
-    ----------
-    mutually_exclusive : bool, default=False
-        Set to True if the extensions are mutually exclusive (e.g. .nii and .nii.gz)
-        when you cannot have 2 data files that only differ by extension.
-
-    See make_filename_template for other parameters description.
-    """
-    if isinstance(extensions, str):
-        extensions = [extensions]
-
-    ext_headings = _get_extension_headings(schema, extensions)
-
-    extensions = utils.combine_extensions(
-        extensions,
-        html_path=f"{GLOSSARY_PATH}.html",
-        heading_lst=ext_headings,
-        pdf_format=pdf_format,
-    )
-
-    lt, gt = ("<", ">") if pdf_format else ("&lt;", "&gt;")
-
-    return f"{lt}{'|'.join(extensions)}{gt}" if mutually_exclusive else extensions
-
-
-def _get_extension_headings(schema: Namespace, extensions: list[str]) -> list[str]:
-    """The glossary indexes by the extension identifier (niigz instead of .nii.gz),
-    but the rules reference the actual suffix string (.nii.gz instead of niigz),
-    so we need to look it up."""
-    ext_key_table = _value_key_table(schema.objects.extensions)
-    ext_headings = []
-    for extension in extensions:
-        key = ext_key_table.get(extension)
-        if key:
-            ext_headings.append(f"{key.lower()}-extensions")
-        else:
-            ext_headings.append("extension-common_principles")
-    return ext_headings
-
-
-def _nb_extensions(group) -> int:
-    return len(_listify_all_extensions(group.extensions))
-
-
-def _listify_all_extensions(extensions: list[str | list[str]]) -> list[str]:
-    tmp = []
-    for ext in extensions:
-        if isinstance(ext, str):
-            tmp.append(ext)
-        else:
-            tmp.extend(ext)
-    return [ext if ext != "*" else ".<extension>" for ext in tmp]
-
-
 def _append_filename_template_legend(text: str, pdf_format=False) -> str:
     """Append a legend to filename templates.
 

From d8e3ec6f1faa9e93a7177d5c0befa15333853462 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Mon, 29 May 2023 15:14:24 -0400
Subject: [PATCH 13/22] update README

---
 src/schema/README.md | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/src/schema/README.md b/src/schema/README.md
index 35ac834c14..7d1adcb0ef 100644
--- a/src/schema/README.md
+++ b/src/schema/README.md
@@ -601,10 +601,7 @@ README:
   level: required
   stem: README
   extensions:
-    - ''
-    - .md
-    - .rst
-    - .txt
+    - ['', '.md', '.rst', '.txt']
 ```
 
 Here, `README` and `README.md` are both valid, while only `dataset_description.json` is permitted.

From e38390522109f411f0c55044cf9bf456351b0fea Mon Sep 17 00:00:00 2001
From: Chris Markiewicz <effigies@gmail.com>
Date: Wed, 31 May 2023 11:56:39 -0400
Subject: [PATCH 14/22] TEST: Fix rendering tests

Update expected number of lines, remove unused tests.
---
 .../bidsschematools/tests/test_render_text.py | 38 +------------------
 1 file changed, 1 insertion(+), 37 deletions(-)

diff --git a/tools/schemacode/bidsschematools/tests/test_render_text.py b/tools/schemacode/bidsschematools/tests/test_render_text.py
index 35437b796b..4ee1f47f6b 100644
--- a/tools/schemacode/bidsschematools/tests/test_render_text.py
+++ b/tools/schemacode/bidsschematools/tests/test_render_text.py
@@ -138,7 +138,7 @@ def test_make_filename_template_mutually_combine_extensions_when_too_many():
     )
     print(filename_template)
     nb_lines = len(filename_template.split("\n"))
-    assert nb_lines == 10
+    assert nb_lines == 14
 
 
 def test_define_common_principles(schema_obj):
@@ -179,39 +179,3 @@ def test_render_text(schema_obj):
 def test_render_text_errors(schema_obj):
     with pytest.raises(ValueError, match="does not refer to a text field"):
         text.render_text(schema_obj, key="dataset_description", src_path=None)
-
-
-@pytest.mark.parametrize(
-    "extensions, expected, pdf_format",
-    [
-        (
-            ["json"],
-            ['<a href="SPEC_ROOT/glossary.html#extension-common_principles">json</a>'],
-            False,
-        ),
-        (["nii.gz", "nii", "json"], ["nii[.gz]", "json"], True),
-    ],
-)
-def test_extension_for_this_group(schema_obj, extensions, expected, pdf_format):
-    extensions = text._combine_extensions_with_headings(
-        schema_obj, extensions, pdf_format=pdf_format
-    )
-    assert extensions == expected
-
-
-class Group:
-    def __init__(self, extensions):
-        self.extensions = extensions
-
-
-@pytest.mark.parametrize("extensions, expected", [(["nii"], 1), (["nii", ["bar", "baz"]], 3)])
-def test_nb_extensions(extensions, expected):
-    group = Group(extensions=extensions)
-    assert text._nb_extensions(group) == expected
-
-
-@pytest.mark.parametrize(
-    "extensions, expected", [(["nii"], ["nii"]), (["nii", ["bar", "baz"]], ["nii", "bar", "baz"])]
-)
-def test_listify_all_extensions(extensions, expected):
-    assert text._listify_all_extensions(extensions) == expected

From a8bd1c363ad033c2e9554b59bd76ecc46fa4c082 Mon Sep 17 00:00:00 2001
From: Chris Markiewicz <effigies@gmail.com>
Date: Tue, 30 May 2023 10:31:45 -0400
Subject: [PATCH 15/22] RF: Convert extensions to lists-of-lists-of-strings

Adjust tests and validator code
---
 .../bidsschematools/data/tests/test_rules.py  | 20 +++++++--------
 tools/schemacode/bidsschematools/rules.py     | 18 ++++++-------
 tools/schemacode/bidsschematools/schema.py    | 25 +++++++++++++++++++
 .../bidsschematools/tests/test_rules.py       | 16 ++++++------
 4 files changed, 51 insertions(+), 28 deletions(-)

diff --git a/tools/schemacode/bidsschematools/data/tests/test_rules.py b/tools/schemacode/bidsschematools/data/tests/test_rules.py
index c44634f814..82b05c6dc8 100644
--- a/tools/schemacode/bidsschematools/data/tests/test_rules.py
+++ b/tools/schemacode/bidsschematools/data/tests/test_rules.py
@@ -59,6 +59,13 @@ def test_rule_objects(schema_obj):
         if not type_instances_in_rules:
             continue
 
+        if object_type in ["extensions", "suffixes"]:
+            # Some object types are referenced via their "value" fields in the rules
+            object_values = {obj.value for obj in schema_obj.objects[object_type].values()}
+        else:
+            # But other object types are referenced via their keys
+            object_values = schema_obj.objects[object_type].keys()
+
         for type_instance in type_instances_in_rules:
             path, instance = type_instance
             is_list = True
@@ -66,6 +73,9 @@ def test_rule_objects(schema_obj):
                 instance = list(instance)
                 is_list = False
 
+            if object_type == "extensions":
+                instance = [ext for group in instance for ext in group]
+
             for i_use, use in enumerate(instance):
                 if use == "derivatives":
                     # Skip derivatives dirs, because the dir is treated as a "use" instead.
@@ -79,16 +89,6 @@ def test_rule_objects(schema_obj):
                     # This test can't handle this yet, so skip.
                     continue
 
-                if object_type in ["extensions", "suffixes"]:
-                    # Some object types are referenced via their "value" fields in the rules
-                    object_values = [
-                        schema_obj["objects"][object_type][k]["value"]
-                        for k in schema_obj["objects"][object_type].keys()
-                    ]
-                else:
-                    # But other object types are referenced via their keys
-                    object_values = list(schema_obj["objects"][object_type].keys())
-
                 # Build a list of items mentioned in rules, but not found in objects.
                 if use not in object_values:
                     temp_path = path[:]
diff --git a/tools/schemacode/bidsschematools/rules.py b/tools/schemacode/bidsschematools/rules.py
index 29bf5cb164..15b2ef2472 100644
--- a/tools/schemacode/bidsschematools/rules.py
+++ b/tools/schemacode/bidsschematools/rules.py
@@ -106,8 +106,10 @@ def _entity_rule(rule: Mapping, schema: bst.types.Namespace):
     suffix_regex = f"(?P<suffix>{'|'.join(suffixes)})"
 
     # If we move to referring to extensions by keys in the object table:
-    # extensions = [schema.objects.extensions[ext].value for ext in rule["extensions"]]
-    extensions = rule["extensions"]
+    # extensions = [
+    #     schema.objects.extensions[ext].value for group in rule["extensions"] for ext in group
+    # ]
+    extensions = [ext for group in rule["extensions"] for ext in group]
     ext_match = "|".join(_sanitize_extension(ext) for ext in extensions)
     ext_regex = f"(?P<extension>{ext_match})"
 
@@ -123,7 +125,7 @@ def _split_inheritance_rules(rule: Mapping) -> ty.List[Mapping]:
     Implements the inheritance principle for file naming.
     """
     heritable_exts = {".tsv", ".json", ".bval", ".bvec"}
-    rule_exts = set(rule["extensions"])
+    rule_exts = {ext for group in rule["extensions"] for ext in group}
 
     main_exts = rule_exts - heritable_exts
     # If a rule only has TSV or JSON files, entities can be
@@ -141,11 +143,11 @@ def _split_inheritance_rules(rule: Mapping) -> ty.List[Mapping]:
     sidecar_dtypes = [""] + rule.get("datatypes", [])
     sidecar_entities = {ent: "optional" for ent in rule["entities"]}
 
-    main_rule = {**rule, **{"extensions": list(main_exts)}}
+    main_rule = {**rule, **{"extensions": [list(main_exts)]}}
     sidecar_rule = {
         **rule,
         **{
-            "extensions": list(sidecar_exts),
+            "extensions": [list(sidecar_exts)],
             "datatypes": sidecar_dtypes,
             "entities": sidecar_entities,
         },
@@ -162,11 +164,7 @@ def _sanitize_extension(ext: str) -> str:
 
 def _stem_rule(rule: bst.types.Namespace):
     stem_regex = re.escape(rule.stem)
-    if isinstance(rule.extensions[0], list) and len(rule.extensions) == 1:
-        extensions = rule.extensions[0]
-    else:
-        extensions = rule.extensions
-    ext_match = "|".join(_sanitize_extension(ext) for ext in extensions)
+    ext_match = "|".join(_sanitize_extension(ext) for group in rule.extensions for ext in group)
     ext_regex = f"(?P<extension>{ext_match})"
 
     return {"regex": stem_regex + ext_regex, "mandatory": rule.level == "required"}
diff --git a/tools/schemacode/bidsschematools/schema.py b/tools/schemacode/bidsschematools/schema.py
index bbae2e5940..698bf4704c 100644
--- a/tools/schemacode/bidsschematools/schema.py
+++ b/tools/schemacode/bidsschematools/schema.py
@@ -15,6 +15,16 @@
 logging.basicConfig(format="%(asctime)-15s [%(levelname)8s] %(message)s")
 
 
+def listify(obj):
+    """Convert string or list of strings into a list of strings"""
+    if isinstance(obj, str):
+        return [obj]
+    if isinstance(obj, list):
+        return obj
+
+    raise ValueError("Unknown object to listify")
+
+
 class BIDSSchemaError(Exception):
     """Errors indicating invalid values in the schema itself"""
 
@@ -97,6 +107,20 @@ def dereference(namespace, inplace=True):
     return namespace
 
 
+def uniformize(namespace: Namespace, inplace=True) -> Namespace:
+    """Expand shorthand schema entries into uniform types
+
+    Currently:
+
+    * Changes single strings in extensions lists into lists of length 1
+    """
+    if not inplace:
+        namespace = deepcopy(namespace)
+    for struct in _find(namespace.rules.files, lambda obj: "extensions" in obj):
+        struct.extensions[:] = [listify(group) for group in struct.extensions]
+    return namespace
+
+
 def flatten_enums(namespace, inplace=True):
     """Replace enum collections with a single enum, merging enums contents.
 
@@ -171,6 +195,7 @@ def load_schema(schema_path=None):
 
     dereference(schema)
     flatten_enums(schema)
+    uniformize(schema)
 
     schema["bids_version"] = _get_bids_version(schema_path)
     schema["schema_version"] = _get_schema_version(schema_path)
diff --git a/tools/schemacode/bidsschematools/tests/test_rules.py b/tools/schemacode/bidsschematools/tests/test_rules.py
index 693c4b24fe..62aee19789 100644
--- a/tools/schemacode/bidsschematools/tests/test_rules.py
+++ b/tools/schemacode/bidsschematools/tests/test_rules.py
@@ -10,7 +10,7 @@ def test_entity_rule(schema_obj):
             "datatypes": ["anat"],
             "entities": {"subject": "required", "session": "optional"},
             "suffixes": ["T1w"],
-            "extensions": [".nii"],
+            "extensions": [[".nii"]],
         }
     )
     assert rules._entity_rule(rule, schema_obj) == {
@@ -32,7 +32,7 @@ def test_entity_rule(schema_obj):
             "datatypes": ["anat", ""],
             "entities": {"subject": "optional", "session": "optional"},
             "suffixes": ["T1w"],
-            "extensions": [".json"],
+            "extensions": [[".json"]],
         }
     )
     assert rules._entity_rule(rule, schema_obj) == {
@@ -54,7 +54,7 @@ def test_split_inheritance_rules():
         "datatypes": ["anat"],
         "entities": {"subject": "required", "session": "optional"},
         "suffixes": ["T1w"],
-        "extensions": [".nii", ".json"],
+        "extensions": [[".nii"], [".json"]],
     }
 
     main, sidecar = rules._split_inheritance_rules(rule)
@@ -62,13 +62,13 @@ def test_split_inheritance_rules():
         "datatypes": ["anat"],
         "entities": {"subject": "required", "session": "optional"},
         "suffixes": ["T1w"],
-        "extensions": [".nii"],
+        "extensions": [[".nii"]],
     }
     assert sidecar == {
         "datatypes": ["", "anat"],
         "entities": {"subject": "optional", "session": "optional"},
         "suffixes": ["T1w"],
-        "extensions": [".json"],
+        "extensions": [[".json"]],
     }
 
     # Can't split again
@@ -77,19 +77,19 @@ def test_split_inheritance_rules():
         "datatypes": ["anat"],
         "entities": {"subject": "required", "session": "optional"},
         "suffixes": ["T1w"],
-        "extensions": [".nii"],
+        "extensions": [[".nii"]],
     }
 
 
 def test_stem_rule():
-    rule = Namespace.build({"stem": "README", "level": "required", "extensions": ["", ".md"]})
+    rule = Namespace.build({"stem": "README", "level": "required", "extensions": [["", ".md"]]})
     assert rules._stem_rule(rule) == {
         "regex": r"README(?P<extension>|\.md)",
         "mandatory": True,
     }
 
     rule = Namespace.build(
-        {"stem": "participants", "level": "optional", "extensions": [".tsv", ".json"]}
+        {"stem": "participants", "level": "optional", "extensions": [[".tsv"], [".json"]]}
     )
     assert rules._stem_rule(rule) == {
         "regex": r"participants(?P<extension>\.tsv|\.json)",

From 586cd18e30b3af97e1c5ef986f0f74eb71f847e6 Mon Sep 17 00:00:00 2001
From: Chris Markiewicz <effigies@gmail.com>
Date: Wed, 31 May 2023 12:33:30 -0400
Subject: [PATCH 16/22] FIX: .mhd files are actually .raw.mhd

---
 src/schema/objects/extensions.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/schema/objects/extensions.yaml b/src/schema/objects/extensions.yaml
index 1a0dc4d299..16bade79ba 100644
--- a/src/schema/objects/extensions.yaml
+++ b/src/schema/objects/extensions.yaml
@@ -156,7 +156,7 @@ mefd:
 
     Each recording consists of a `.mefd` directory.
 mhd:
-  value: .mhd
+  value: .raw.mhd
   display_name: ITAB Binary Header
   description: |
     Produced by ITAB-ARGOS153 systems. This file a binary header file, and is generated along with a

From 1fbb60b1cc473f270ec0c27a1888f289c26f62a7 Mon Sep 17 00:00:00 2001
From: Chris Markiewicz <effigies@gmail.com>
Date: Tue, 6 Jun 2023 14:03:11 -0400
Subject: [PATCH 17/22] MNT: Bump schema minor version to mark change to
 structure

---
 src/schema/SCHEMA_VERSION | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/schema/SCHEMA_VERSION b/src/schema/SCHEMA_VERSION
index c7d2522718..f8d71478f5 100644
--- a/src/schema/SCHEMA_VERSION
+++ b/src/schema/SCHEMA_VERSION
@@ -1 +1 @@
-0.7.2-dev
+0.8.0-dev

From 53c4fd3797b45aab8f1b4193dd5196522baaefda Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Mon, 3 Jul 2023 18:12:57 +0200
Subject: [PATCH 18/22] Update src/schema/rules/files/raw/photo.yaml

Co-authored-by: Chris Markiewicz <effigies@gmail.com>
---
 src/schema/rules/files/raw/photo.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/schema/rules/files/raw/photo.yaml b/src/schema/rules/files/raw/photo.yaml
index 6529ed3c76..9fddef1ddf 100644
--- a/src/schema/rules/files/raw/photo.yaml
+++ b/src/schema/rules/files/raw/photo.yaml
@@ -17,7 +17,7 @@ photo:
 photo__micr:
   $ref: rules.files.raw.photo.photo
   extensions:
-    - [.jpg, .png, .tif]
+    - $ref: rules.files.raw.photo.photo.extensions
     - .json
   datatypes:
     - micr

From da67b35dd976f6bfe12cb6053ba325fdff12f259 Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Thu, 10 Aug 2023 15:21:04 -0400
Subject: [PATCH 19/22] remove digitizer

---
 .../magnetoencephalography.md                    |  2 +-
 src/schema/objects/suffixes.yaml                 |  4 ----
 src/schema/rules/files/raw/meg.yaml              | 16 ----------------
 3 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/src/modality-specific-files/magnetoencephalography.md b/src/modality-specific-files/magnetoencephalography.md
index fc42d318db..6f0b4c0baa 100644
--- a/src/modality-specific-files/magnetoencephalography.md
+++ b/src/modality-specific-files/magnetoencephalography.md
@@ -26,7 +26,7 @@ and a guide for using macros can be found at
 {{ MACROS___make_filename_template(
    "raw",
    datatypes=["meg"],
-   suffixes=["meg", "markers", "events", "physio", "stim", "digitizer"])
+   suffixes=["meg", "markers", "events", "physio", "stim"])
 }}
 
 Unprocessed MEG data MUST be stored in the native file format of the MEG
diff --git a/src/schema/objects/suffixes.yaml b/src/schema/objects/suffixes.yaml
index 9588b93ceb..caa943ee7c 100644
--- a/src/schema/objects/suffixes.yaml
+++ b/src/schema/objects/suffixes.yaml
@@ -551,10 +551,6 @@ defacemask:
   description: |
     A binary mask that was used to remove facial features from an anatomical MRI
     image.
-digitizer:
-  value: digitizer
-  display_name: Digitizer
-  description: Digitized positions of the head points.
 dseg:
   value: dseg
   display_name: Discrete Segmentation
diff --git a/src/schema/rules/files/raw/meg.yaml b/src/schema/rules/files/raw/meg.yaml
index 5458beb551..3535190363 100644
--- a/src/schema/rules/files/raw/meg.yaml
+++ b/src/schema/rules/files/raw/meg.yaml
@@ -23,22 +23,6 @@ meg:
     processing: optional
     split: optional
 
-headpoints:
-  suffixes:
-    - digitizer
-  extensions:
-    - .txt
-  datatypes:
-    - meg
-  entities:
-    subject: required
-    session: optional
-    task: required
-    acquisition: optional
-    run: optional
-    processing: optional
-    split: optional
-
 calibration:
   suffixes:
     - meg

From 6c092d8829e13eeae9f69e9e5902e82d48ded48e Mon Sep 17 00:00:00 2001
From: Remi Gau <remi_gau@hotmail.com>
Date: Thu, 10 Aug 2023 16:32:54 -0400
Subject: [PATCH 20/22] fix some failing tests

---
 tools/schemacode/bidsschematools/render/text.py |  8 +++++++-
 tools/schemacode/bidsschematools/rules.py       | 13 +++++++++++--
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index 9e8f2f3ab7..00c1cb9e1a 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -398,11 +398,17 @@ def make_filename_template(
                 ]
 
             # Add extensions
+            extensions = []
+            for x in group.extensions:
+                if isinstance(x[0], str):
+                    extensions.append(x[0])
+                if isinstance(x[0], list):
+                    extensions.extend(iter(x[0]))
             extension_groups = [
                 [".<extension>" if ext == "*" else ext]
                 if isinstance(ext, str)
                 else ([".<extension>"] if len(ext) >= n_dupes_to_combine else ext)
-                for ext in group.extensions
+                for ext in extensions
             ]
             for ext_group in sorted(extension_groups):
                 ext_headings = []
diff --git a/tools/schemacode/bidsschematools/rules.py b/tools/schemacode/bidsschematools/rules.py
index 141615f9c8..55769a597c 100644
--- a/tools/schemacode/bidsschematools/rules.py
+++ b/tools/schemacode/bidsschematools/rules.py
@@ -136,9 +136,18 @@ def _split_inheritance_rules(rule: Mapping) -> ty.List[Mapping]:
 
     Implements the inheritance principle for file naming.
     """
-    heritable_exts = {".tsv", ".json", ".bval", ".bvec"}
-    rule_exts = {ext for group in rule["extensions"] for ext in group}
 
+    extensions = []
+    for x in rule["extensions"]:
+        if isinstance(x[0], str):
+            extensions.append(x[0])
+        if isinstance(x[0], list):
+            extensions.extend(iter(x[0]))
+    extensions = [extensions]
+
+    rule_exts = {ext for group in extensions for ext in group}
+
+    heritable_exts = {".tsv", ".json", ".bval", ".bvec"}
     main_exts = rule_exts - heritable_exts
     # If a rule only has TSV or JSON files, entities can be
     # made required

From f297c3098558dbbd3ea117bc1a7c3bc1f6801626 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 8 Aug 2024 00:12:19 +0000
Subject: [PATCH 21/22] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/schema/SCHEMA_VERSION                       | 2 +-
 tools/schemacode/bidsschematools/render/text.py | 8 +++++---
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/src/schema/SCHEMA_VERSION b/src/schema/SCHEMA_VERSION
index 19a5fa4373..eb1336c84d 100644
--- a/src/schema/SCHEMA_VERSION
+++ b/src/schema/SCHEMA_VERSION
@@ -1 +1 @@
-0.11.0-dev
\ No newline at end of file
+0.11.0-dev
diff --git a/tools/schemacode/bidsschematools/render/text.py b/tools/schemacode/bidsschematools/render/text.py
index fbb0be43f2..6aaf7ea52e 100644
--- a/tools/schemacode/bidsschematools/render/text.py
+++ b/tools/schemacode/bidsschematools/render/text.py
@@ -407,9 +407,11 @@ def make_filename_template(
                 if isinstance(x[0], list):
                     extensions.extend(iter(x[0]))
             extension_groups = [
-                [".<extension>" if ext == "*" else ext]
-                if isinstance(ext, str)
-                else ([".<extension>"] if len(ext) >= n_dupes_to_combine else ext)
+                (
+                    [".<extension>" if ext == "*" else ext]
+                    if isinstance(ext, str)
+                    else ([".<extension>"] if len(ext) >= n_dupes_to_combine else ext)
+                )
                 for ext in extensions
             ]
             for ext_group in sorted(extension_groups):

From 3958ac0efdfd7af771e5097d2e33ce07eb87ef3e Mon Sep 17 00:00:00 2001
From: Chris Markiewicz <effigies@gmail.com>
Date: Wed, 7 Aug 2024 21:03:38 -0400
Subject: [PATCH 22/22] fix: Adapt to extensions being list[list[str]]

---
 src/metaschema.json                                  |  4 ++--
 tools/schemacode/bidsschematools/rules.py            | 10 +---------
 tools/schemacode/bidsschematools/schema.py           |  6 +++++-
 tools/schemacode/bidsschematools/tests/test_rules.py |  2 +-
 4 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/src/metaschema.json b/src/metaschema.json
index c0462edcaf..708f547cb9 100644
--- a/src/metaschema.json
+++ b/src/metaschema.json
@@ -657,7 +657,7 @@
           "items": { "pattern": "^[a-z]+$" }
         },
         "stem": { "type": "string" },
-        "extensions": { "type": "array", "items": { "type": "string" } }
+        "extensions": { "type": "array", "items": { "type": "array", "items": { "type": "string" } } }
       },
       "required": ["level", "stem", "extensions"],
       "additionalProperties": false
@@ -674,7 +674,7 @@
           "type": "array",
           "items": { "pattern": "^[a-zA-Z0-9]+$" }
         },
-        "extensions": { "type": "array", "items": { "type": "string" } },
+        "extensions": { "type": "array", "items": { "type": "array", "items": { "type": "string" } } },
         "entities": {
           "type": "object",
           "patternProperties": {
diff --git a/tools/schemacode/bidsschematools/rules.py b/tools/schemacode/bidsschematools/rules.py
index d28fc8de36..ad3ad83340 100644
--- a/tools/schemacode/bidsschematools/rules.py
+++ b/tools/schemacode/bidsschematools/rules.py
@@ -139,15 +139,7 @@ def _split_inheritance_rules(rule: dict) -> ty.List[dict]:
     Implements the inheritance principle for file naming.
     """
 
-    extensions = []
-    for x in rule["extensions"]:
-        if isinstance(x[0], str):
-            extensions.append(x[0])
-        if isinstance(x[0], list):
-            extensions.extend(iter(x[0]))
-    extensions = [extensions]
-
-    rule_exts = {ext for group in extensions for ext in group}
+    rule_exts = set(sum(rule["extensions"], []))
 
     heritable_exts = {".tsv", ".json", ".bval", ".bvec"}
     main_exts = rule_exts - heritable_exts
diff --git a/tools/schemacode/bidsschematools/schema.py b/tools/schemacode/bidsschematools/schema.py
index 128640831d..5b0fc6662d 100644
--- a/tools/schemacode/bidsschematools/schema.py
+++ b/tools/schemacode/bidsschematools/schema.py
@@ -137,7 +137,11 @@ def dereference(namespace, inplace=True):
             except (AttributeError, KeyError):
                 pass
             else:
-                struct[i] = namespace.get(target)
+                value = namespace.get(target)
+                if isinstance(value, list):
+                    struct[i : i + 1] = value
+                else:
+                    struct[i] = value
 
     return namespace
 
diff --git a/tools/schemacode/bidsschematools/tests/test_rules.py b/tools/schemacode/bidsschematools/tests/test_rules.py
index a9523e2678..47dc36794a 100644
--- a/tools/schemacode/bidsschematools/tests/test_rules.py
+++ b/tools/schemacode/bidsschematools/tests/test_rules.py
@@ -102,7 +102,7 @@ def test_stem_rule():
             "stem": "*",
             "datatypes": ["phenotype"],
             "level": "optional",
-            "extensions": [".tsv", ".json"],
+            "extensions": [[".tsv"], [".json"]],
         }
     )
     assert rules._stem_rule(rule) == {