1 files changed, 112 insertions, 0 deletions
diff --git a/helpers.py b/helpers.py
index faf14e7..162d39e 100644
--- a/helpers.py
+++ b/helpers.py
@@ -1,5 +1,17 @@
+from dataclasses import dataclass
+from datetime import datetime
+from operator import attrgetter
 from os import path
 from pathlib import Path
+import re
+from typing import Iterator, Optional
+
+
+def guess_language(filename):
+    parent = str(Path(filename).parent)
+    if parent == '.':
+        return 'fr'
+    return parent
 
 
 def relative_path(*, to, ref):
@@ -7,3 +19,103 @@ def relative_path(*, to, ref):
     # os.path.dirname('x') yields '' rather than '.'.
     # 😮‍💨
     return path.relpath(to, Path(ref).parent)
+
+
+_LICENSE_URLS = {
+    'CC0': 'https://creativecommons.org/publicdomain/zero',
+    'CC BY': 'https://creativecommons.org/licenses/by',
+    'CC BY-SA': 'https://creativecommons.org/licenses/by-sa',
+}
+
+_LICENSE_RE = re.compile(
+    '('+'|'.join(_LICENSE_URLS.keys())+')' + ' ([0-9.]+)'
+)
+
+@dataclass
+class LicenseInfo:
+    tag: str
+    version: str
+
+    @classmethod
+    def deserialize(cls, info):
+        if info is None:
+            return None
+        return cls(*_LICENSE_RE.fullmatch(info).groups())
+
+    def format(self):
+        url = f'{_LICENSE_URLS[self.tag]}/{self.version}/'
+
+        return f'<a href="{url}" target="_blank">{self.tag}</a>'
+
+
+@dataclass
+class Illustration:
+    file: str
+    alt_text: str
+    source_name: str
+    source_link: Optional[str]
+    license_info: Optional[LicenseInfo]
+
+    @classmethod
+    def deserialize(cls, d):
+        return cls(d['pic_file'],
+                   d['pic_alt'],
+                   d['pic_src'],
+                   d['pic_link'],
+                   LicenseInfo.deserialize(d['pic_license']))
+
+
+@dataclass
+class Concert:
+    time: datetime
+    place: str
+    address: str
+    pieces: Iterator[str]
+    instructions: str
+    illustration: Illustration
+    warning: Optional[str]
+
+    @classmethod
+    def deserialize(cls, d):
+        return cls(
+            time=datetime.strptime(d['time'], '%d/%m/%Y %Hh%M'),
+            place=d['place'],
+            address=d['address'],
+            pieces=d['pieces'],
+            instructions=d['instructions'],
+            illustration=Illustration.deserialize(d),
+            warning=d['warning']
+        )
+
+
+def _optional(line):
+    return f'(?:{line})?'
+
+_CONCERT_LINES = (
+    r'QUAND : (?P<time>[^\n]+)\n',
+    r'O[UÙ] : (?P<place>[^\n]+)\n',
+    'ADRESSE :\n',
+    '(?P<address>.+?)\n',
+    'PROGRAMME :\n',
+    '(?P<pieces>.+?)\n',
+    'INSTRUCTIONS :\n',
+    '(?P<instructions>.+?)\n',
+    'ILLUSTRATION :\n',
+    r'fichier : (?P<pic_file>[^\n]+)\n',
+    r'légende : (?P<pic_alt>[^\n]+)\n',
+    r'source : (?P<pic_src>[^\n]+)\n',
+    _optional(r'lien : (?P<pic_link>[^\n]+)\n'),
+    _optional(r'licence : (?P<pic_license>[^\n]+)\n'),
+    _optional(r'AVERTISSEMENT : (?P<warning>[^\n]+)\n'),
+)
+
+_CONCERT_RE = re.compile(''.join(_CONCERT_LINES), flags=re.DOTALL)
+
+
+def read_concerts(filename):
+    with open(filename) as f:
+        concerts = (
+            Concert.deserialize(match)
+            for match in re.finditer(_CONCERT_RE, f.read())
+        )
+        return tuple(sorted(concerts, key=attrgetter('time')))