Initial commit

.github/workflows/text-validation.yml

@@ -0,0 +1,19 @@
+name: Text validation
+
+on: [push, pull_request]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python 3.8
+      uses: actions/setup-python@v1
+      with:
+        python-version: 3.8
+    - name: Run text
+      run: |
+        pip install text-validator
+        validate-text text-validator.toml text/*.txt

README.md

@@ -0,0 +1,21 @@
+# {{ NAME OF TEXT }}
+
+{{ describe what is being done, the process being followed, and who is involved in the work }}
+
+This text is being prepared as part of the [Greek Learner Texts Project](https://greek-learner-texts.org/).
+
+## Contributors
+
+* {{ list of people who have contributed to this repo }}
+
+## Source
+
+{{ indicate original source(s) of text: scans or existing transcriptions }}
+
+## Progress
+
+{{ indicate progress, or remove entire section if done }}
+
+## License
+
+This work is licensed under a [Creative Commons Attribution-ShareAlike 4.0 International License](http://creativecommons.org/licenses/by-sa/4.0/).

analysis/README

@@ -0,0 +1 @@
+Token-level analysis like lemmatisation or postagging can go here.

docs/README

@@ -0,0 +1 @@
+Generated HTML versions of the texts should go here.

orig/README

@@ -0,0 +1 @@
+Any original files (scans and transcriptions) can be placed here.

scripts/README

@@ -0,0 +1 @@
+Any scripts used in the preparation of the texts can go here.

text-validator.toml

@@ -0,0 +1,28 @@
+["text_validator.plugins.whitespace"]
+CHECK_CRLF = true
+CHECK_TABS = true
+CHECK_TRAILING_WHITESPACE = true
+CHECK_NO_EOF_NEWLINE = true
+
+["text_validator.plugins.unicode"]
+CONFIRM_UTF_8_NFC = true
+
+["text_validator.plugins.ref_line_format"]
+REF_REGEX = "\\d+\\.\\d+$"
+
+["text_validator.plugins.characters"]
+REPLACE_CHARS = [
+    # bad character, suggested replacement
+    ["\u02BC", "\u2019"],
+    ["\u1FBF", "\u2019"],
+    ["\u037E", "\u003B"],
+    ["\u0387", "\u00B7"],
+    ["\u0374", "\u02B9"],
+    ["\u03D5", "\u03C6"],
+    ["\u03D1", "\u03B8"],
+]
+TOKEN_REGEXES = [
+    # each whitespace-separated token must match one of these regexes
+    "\\d+\\.\\d+$",
+    "[«(]*[\u0370-\u03FF\u1F00-\u1FFF]+\u2019?[.,:;»)·]*$",
+]

text/README

@@ -0,0 +1,2 @@
+* the prepared text in our textpart-per-line format with dotted ref
+* can be multiple *.txt files but, if there is an inherent order to the files, this should be reflected in the sort order of the filenames