[SCHEMA] Add patterns for format validation

src/schema/formats.yaml

@@ -0,0 +1,88 @@
+---
+# This file defines valid patterns for different formats
+# Entity patterns
+label:
+  description: |
+    Freeform labels without special characters.
+  pattern: ^[0-9a-zA-Z]+$
+index:
+  description: |
+    Non-negative, non-zero integers, optionally prefixed with leading zeros for sortability.
+    An index may not be all zeros.
+  pattern: ^[0-9]*[1-9]+[0-9]*$
+# Metadata types
+string:
+  description: |
+    The basic string type (not a specific format).
+    This should allow any free-form string *except* "n/a".
+  pattern: ^(?!(n/a)$).*$
+integer:
+  description: |
+    An integer which may be positive or negative.
+  pattern: ^[+-]?\d+$
+number:
+  description: |
+    A number which may be an integer or float, positive or negative.
+  pattern: ^[+-]?([0-9]+([.][0-9]*)?|[.][0-9]+)$
+boolean:
+  description: |
+    A boolean.
+    Must be either "true" or "false".
+  pattern: ^(true|false)$
+# String formats
+date:
+  description: |
+    A date in the form YYYY-MM-DD[Z],
+    where [Z] is an optional, valid timezone code.
+  pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}?([A-Z]{3,4})$
+datetime:
+  description: |
+    A datetime in the form YYYY-MM-DDThh:mm:ss[.000000][Z],
+    where [.000000] is an optional subsecond resolution between 1 and 6 decimal points,
+    and [Z] is an optional, valid timezone code.
+  pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}?(\.[0-9]{1,6})?([A-Z]{3,4})$
+unit:
+  description: |
+    A unit.
+    Currently this matches any string that isn't "n/a".
+
+    TODO: Somehow reference the actual unit options in the Units appendix.
+  pattern: ^(?!(n/a)$).*$
+stimuli_relative:
+  description: |
+    A path to a stimulus file, relative to a `/stimuli` folder somewhere.
+
+    The validation for this format is minimal.
+    It simply ensures that the value is a string with any characters that may appear in a valid path,
+    without starting with "/" (an absolute path) or "stimuli/"
+    (a relative path starting with the stimuli folder, rather than relative to that folder).
+  pattern: ^(?!/)(?!stimuli/)[0-9a-zA-Z/\_\-\.]+$
+dataset_relative:
+  description: |
+    A path to a file, relative to the dataset folder.
+
+    The validation for this format is minimal.
+    It simply ensures that the value is a string with any characters that may appear in a valid path,
+    without starting with "/" (an absolute path).
+  pattern: ^(?!/)[0-9a-zA-Z/\_\-\.]+$
+participant_relative:
+  description: |
+    A path to a file, relative to the participant's folder in the dataset.
+
+    The validation for this format is minimal.
+    It simply ensures that the value is a string with any characters that may appear in a valid path,
+    without starting with "/" (an absolute path) or "sub/"
+    (a relative path starting with the participant folder, rather than relative to that folder).
+  pattern: ^(?!/)(?!sub-)[0-9a-zA-Z/\_\-\.]+$
+uri:
+  description: |
+    A uniform resource indicator.
+  pattern: ^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?
+bids_uri:
+  description: |
+    A BIDS uniform resource indicator.
+
+    The validation for this format is minimal.
+    It simply ensures that the value is a string with any characters that may appear in a valid URI,
+    starting with "bids:".
+  pattern: ^bids:[0-9a-zA-Z/#:\?\_\-\.]+$