Glosses

README.md

@@ -16,10 +16,10 @@ Cantanhêde, S. d. O., Naaijer, M., Højgaard, C. C., & Glanz, O. (2026). Identi
 
 ### Use of the dataset
 
-You can use the dataset freely for research and education. If you do so, please refer to the paper. Also refer to the dataset in the following way:
+You can use the dataset freely for research and education. If you do so, please refer to the papers. Also refer to the dataset in the following way:
 
-Christian Canu Højgaard, Martijn Naaijer, & Stefan Schorch. (2023). 
-Text-Fabric Dataset of the Samaritan Pentateuch. Zenodo. 
+Christian Canu Højgaard, Martijn Naaijer, & Stefan Schorch. (2023).
+Text-Fabric Dataset of the Samaritan Pentateuch. Zenodo.
 https://doi.org/10.5281/zenodo.7734632
 
 You can also refer to specific versions of the dataset.
@@ -70,9 +70,13 @@ Version
 - 6.0.0 February 2026 addition of phrase atoms.
 
 ### Features
-Currently, the following features exist for all books:
+Currently, the following features exist for all books.
+- book
+- chapter
+- verse
 - g_cons
 - lex
+- gloss
 - sp
 - g_vbs
 - g_pfm
@@ -83,11 +87,13 @@ Currently, the following features exist for all books:
 - g_prs
 - vt
 - ps
-- prs_ps
 - nu
-- prs_nu
 - gn
+- prs_ps
+- prs_nu
 - prs_gn
+- language
+- trailer
 
 ### Textual issues
-Some annotations are dubious due to idiosyncracies in the SP manuscript used for this project. The issues are documented in the folder textual_issues.
+Some annotations are dubious due to idiosyncrasies in the SP manuscript used for this project. The issues are documented in the folder textual_issues.

app/config.yaml

@@ -13,7 +13,7 @@ docs:
 interfaceDefaults: {}
 provenanceSpec:
   corpus: The Samaritan Pentateuch
-  version: 6.0.3
+  version: 6.1
 writing: hbo
 typeDisplay:
   verse:

tests/test_general.py

@@ -11,7 +11,7 @@
 
 TF = Fabric(locations=os.path.join(ROOT_DIR, TF_FOLDER, latest_data_folder))
 api = TF.load('''
-    otype g_cons_raw g_cons g_cons_utf8 lex g_pfm g_vbs g_lex g_vbe g_nme g_uvf g_prs sp vt ps nu gn prs_nu prs_ps prs_gn trailer ETCBC_parsing
+    otype g_cons_raw g_cons g_cons_utf8 lex gloss language g_pfm g_vbs g_lex g_vbe g_nme g_uvf g_prs sp vt ps nu gn prs_nu prs_ps prs_gn trailer ETCBC_parsing
 ''')
 api.loadLog()
 api.makeAvailableIn(globals())
@@ -112,6 +112,18 @@ def test_lexemes_advb_conj_prep_pron_nega_inrg_intj_ending():
 def test_lexemes_subs_adjv_ending():
     assert all({F.lex.v(w)[-1] == '/' for w in F.otype.s('word') if F.sp.v(w) in {'subs', 'nmpr', 'adjv'}})
 
+def test_glosses_content():
+    assert all({F.gloss.v(w) != '' for w in F.otype.s('word')})
+
+def test_glosses_consistency(): #Each lexeme may only have one gloss
+    lex_gloss_dict = collections.defaultdict(set)
+    for w in F.otype.s('word'):
+        lex_gloss_dict[F.lex.v(w)].add(F.gloss.v(w))
+    assert all({w for w in lex_gloss_dict if len(lex_gloss_dict[w]) > 1})
+
+def test_language():
+    assert all({F.language.v(w) in {'Hebrew','Aramaic'} for w in F.otype.s('word')})
+
 def test_unexpected_preformative():
     assert all({not F.g_pfm.v(w) for w in F.otype.s('word') if F.sp.v(w) not in {'verb'}})
 
@@ -122,7 +134,7 @@ def test_unexpected_verbal_stem():
     assert all({not F.g_vbs.v(w) for w in F.otype.s('word') if F.sp.v(w) not in {'verb'}})
 
 def test_allowed_verbal_stem():
-    assert all({F.g_vbs.v(w) in {'',']]',']H]',']N]',']T]',']HT]',']W]',']CT]',']HW]',']HCT]',']S]',']>]',']F]',']HF]',']Y]'} for w in F.otype.s('word')})
+    assert all({F.g_vbs.v(w) in {'',']]',']H]',']N]',']T]',']HT]',']W]',']CT]',']HW]',']HCT]',']S]',']>]',']F]',']HF]',']Y]',']X]'} for w in F.otype.s('word')})
 
 def test_expected_verbal_ending():
     assert all({F.g_vbe.v(w) for w in F.otype.s('word') if F.sp.v(w) in {'verb'}})

textual_issues/issues.json

@@ -1 +1 @@
-{"0": {"data_version": "4.1", "tf_node": 412335, "section": ["Genesis", 15, 8], "explanation": "The second yod is interpreted as a dittography, but the first yod may also be a vowel indicator and the second part of the lexeme"}, "1": {"data_version": "4.1", "tf_node": 430624, "section": ["Genesis", 44, 10], "explanation": "The word is interpreted as the verb NQH in Qal passive participle realized with an aleph"}, "2": {"data_version": "4.1", "tf_node": 433530, "section": ["Genesis", 49, 12], "explanation": "Florentin and Tal suggests a plural perfective verb with four radicals(?) or a noun. It is interpreted here simply as a singular, masculine adjective"}, "3": {"data_version": "4.1", "tf_node": 446025, "section": ["Exodus", 19, 24], "explanation": "The word K is interpreted as the imperative of HLK and should have been LK"}, "4": {"data_version": "4.1", "tf_node": 470812, "section": ["Leviticus", 19, 18], "explanation": "FLorentin and Tal interpret the verb as an imperfect of VWR[, but it does not explain the presence of an H in this manuscript"}, "5": {"data_version": "4.1", "tf_node": 490667, "section": ["Numbers", 21, 18], "explanation": "The word is interpreted as a qal perfect of KRH[. To account for the aleph, it as treated as a univalent final"}, "6": {"data_version": "4.1", "tf_node": 492881, "section": ["Numbers", 24, 22], "explanation": "Following Florentin and Tal, the word is interpreted as a noun with pronominal suffix"}, "7": {"data_version": "4.1", "tf_node": 506367, "section": ["Deuteronomy", 9, 21], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "8": {"data_version": "4.1", "tf_node": 508836, "section": ["Deuteronomy", 13, 15], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "9": {"data_version": "4.1", "tf_node": 510499, "section": ["Deuteronomy", 17, 4], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "10": {"data_version": "4.1", "tf_node": 515248, "section": ["Deuteronomy", 27, 8], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "11": {"data_version": "4.1", "tf_node": 518074, "section": ["Deuteronomy", 31, 2], "explanation": "The verb is clearly meant to be BW>[ but the initial > is confusing. We suspect it is a scribal error"}, "12": {"data_version": "4.1", "tf_node": 519665, "section": ["Deuteronomy", 33, 2], "explanation": "According to Florentin and Tal, some manuscripts seperate the word into two with a dot. We do not know if this is the case for this manuscript, and we treat it currently as a single word"}}
+{"0": {"data_version": "4.1", "tf_node": 412335, "section": ["Genesis", 15, 8], "explanation": "The second yod is interpreted as a dittography, but the first yod may also be a vowel indicator and the second part of the lexeme"}, "1": {"data_version": "4.1", "tf_node": 430624, "section": ["Genesis", 44, 10], "explanation": "The word is interpreted as the verb NQH in Qal passive participle realized with an aleph"}, "2": {"data_version": "4.1", "tf_node": 433530, "section": ["Genesis", 49, 12], "explanation": "Florentin and Tal suggests a plural perfective verb with four radicals(?) or a noun. It is interpreted here simply as a singular, masculine adjective"}, "3": {"data_version": "4.1", "tf_node": 446025, "section": ["Exodus", 19, 24], "explanation": "The word K is interpreted as the imperative of HLK and should have been LK"}, "4": {"data_version": "4.1", "tf_node": 470812, "section": ["Leviticus", 19, 18], "explanation": "FLorentin and Tal interpret the verb as an imperfect of VWR[, but it does not explain the presence of an H in this manuscript"}, "5": {"data_version": "4.1", "tf_node": 490667, "section": ["Numbers", 21, 18], "explanation": "The word is interpreted as a qal perfect of KRH[. To account for the aleph, it as treated as a univalent final"}, "6": {"data_version": "4.1", "tf_node": 492881, "section": ["Numbers", 24, 22], "explanation": "Following Florentin and Tal, the word is interpreted as a noun with pronominal suffix"}, "7": {"data_version": "4.1", "tf_node": 506367, "section": ["Deuteronomy", 9, 21], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "8": {"data_version": "4.1", "tf_node": 508836, "section": ["Deuteronomy", 13, 15], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "9": {"data_version": "4.1", "tf_node": 510499, "section": ["Deuteronomy", 17, 4], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "10": {"data_version": "4.1", "tf_node": 515248, "section": ["Deuteronomy", 27, 8], "explanation": "Florentin and Tal follow Ben-Hayyim in calling the H an exclamatory. On the other hand, they consider the verb an adverbial and a non-substantive variation to the Masoretic infinitiv absolute. It is treated here as an hiphil infinitive absolute"}, "11": {"data_version": "4.1", "tf_node": 518074, "section": ["Deuteronomy", 31, 2], "explanation": "The verb is clearly meant to be BW>[ but the initial > is confusing. We suspect it is a scribal error"}, "12": {"data_version": "4.1", "tf_node": 519665, "section": ["Deuteronomy", 33, 2], "explanation": "According to Florentin and Tal, some manuscripts seperate the word into two with a dot. We do not know if this is the case for this manuscript, and we treat it currently as a single word"}, "13": {"data_version": "6.3", "tf_node": 443343, "section": ["Exodus", 15, 6], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "14": {"data_version": "6.3", "tf_node": 443406, "section": ["Exodus", 15, 11], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "15": {"data_version": "6.3", "tf_node": 445973, "section": ["Exodus", 19, 21], "explanation": "Considered a scribal error (substitution) and harmonized with the MT"}, "16": {"data_version": "6.3", "tf_node": 446040, "section": ["Exodus", 19, 24], "explanation": "Considered a scribal error (substitution) and harmonized with the MT"}, "17": {"data_version": "6.3", "tf_node": 453853, "section": ["Exodus", 32, 20], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "18": {"data_version": "6.3", "tf_node": 465206, "section": ["Leviticus", 11, 30], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "19": {"data_version": "6.3", "tf_node": 465209, "section": ["Leviticus", 11, 30], "explanation": "Considered a scribal error (omission) and harmonized with the MT"}, "20": {"data_version": "6.3", "tf_node": 483615, "section": ["Numbers", 11, 5], "explanation": "Considered a scribal error (omission) and harmonized with the MT"}, "21": {"data_version": "6.3", "tf_node": 484093, "section": ["Numbers", 11, 25], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "22": {"data_version": "6.3", "tf_node": 484127, "section": ["Numbers", 11, 26], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "23": {"data_version": "6.3", "tf_node": 484143, "section": ["Numbers", 11, 27], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "24": {"data_version": "6.3", "tf_node": 508812, "section": ["Deuteronomy", 13, 14], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "25": {"data_version": "6.3", "tf_node": 509028, "section": ["Deuteronomy", 14, 5], "explanation": "Considered a scribal error (substitution) and harmonized with the core SP tradition"}, "26": {"data_version": "6.3", "tf_node": 509644, "section": ["Deuteronomy", 15, 9], "explanation": "Considered a scribal error (metathesis) and harmonized with the MT"}, "27": {"data_version": "6.3", "tf_node": 512690, "section": ["Deuteronomy", 21, 20], "explanation": "Considered a scribal error (substitution) and harmonized with the MT"}, "28": {"data_version": "6.3", "tf_node": 519143, "section": ["Deuteronomy", 32, 22], "explanation": "Considered a scribal error and harmonized (substitution) with core SP tradition"}}