X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/102acc0b6eb715826f26b5082611604cf6ebe240..3a536ae0c5aad3f82eb0d344c5f24111532b41ac:/src/catalogue/api/tojson.py?ds=sidebyside

diff --git a/src/catalogue/api/tojson.py b/src/catalogue/api/tojson.py
index 633d4f6bb..b803e73da 100644
--- a/src/catalogue/api/tojson.py
+++ b/src/catalogue/api/tojson.py
@@ -1,3 +1,4 @@
+from collections import defaultdict
 import json
 import re
 from sys import argv
@@ -53,7 +54,7 @@ tags = {
     'osoba': ('em', True, {'class': 'osoba'}, None, None),
     'didaskalia': ('div', True, {'class': 'didaskalia'}, None, None),
     'kwestia': ('div', False, {'class': 'kwestia'}, None, None),
-    'didask_tekst': ('em', False, {'class': 'didask_tekst'}, None, None),
+    'didask_tekst': ('em', True, {'class': 'didask_tekst'}, None, None),
     
     'naglowek_czesc': ('h2', True, None, None, None),
     'naglowek_akt': ('h2', True, None, None, None),
@@ -81,13 +82,68 @@ tags = {
 
     'begin': ('_ignore', True, {'class': 'reference'}, {'data-uri': 'href'}, False),
     'end': ('_ignore', True, {'class': 'reference'}, {'data-uri': 'href'}, False),
-    'motyw': ('a', True, {'class': 'theme'}, None, False),
+    'motyw': ('_ignore', True, {'class': 'theme'}, None, False),
 
     'pa': ('a', True, {'class': 'footnote footnote-pa'}, None, False),
     'pe': ('a', True, {'class': 'footnote footnote-pe'}, None, False),
     'pr': ('a', True, {'class': 'footnote footnote-pr'}, None, False),
     'pt': ('a', True, {'class': 'footnote footnote-pt'}, None, False),
     'ptrad': ('a', True, {'class': 'footnote footnote-ptrad'}, None, False),
+
+    'werset': ('p', True, {'class': 'werset'}, None, True),
+    'br': ('br', False, None, None, None),
+    'indeks_dolny': ('em', True, {'class': 'indeks_dolny'}, None, False),
+    'mat': ('span', True, {'class': 'mat'}, None, False),
+
+    'mfenced': ('math_mfenced', True, None, None, False),
+    'mfrac': ('math_mfrac', True, None, None, False),
+    'mrow': ('math_mrow', True, None, None, False),
+    'mi': ('math_mi', True, None, None, False),
+    'mn': ('math_mn', True, None, None, False),
+    'mo': ('math_mo', True, None, None, False),
+    'msup': ('math_msup', True, None, None, False),
+
+    'list': ('blockquote', False, {'class': 'list'}, None, None),
+    'wywiad_pyt': ('blockquote', False, {'class': 'wywiad_pyt'}, None, None),
+    'wywiad_odp': ('blockquote', False, {'class': 'wywiad_odp'}, None, None),
+    'rownolegle': ('blockquote', False, {'class': 'rownolegle'}, None, None),
+    'animacja': ('div', False, {'class': 'animacja'}, None, None),
+    'data': ('div', True, {'class': 'data'}, None, None),
+    'podpis': ('div', True, {'class': 'podpis'}, None, None),
+    'naglowek_listu': ('div', True, {'class': 'naglowek_listu'}, None, None),
+    'pozdrowienie': ('div', True, {'class': 'pozdrowienie'}, None, None),
+    'adresat': ('div', True, {'class': 'adresat'}, None, None),
+    'tytul_oryg': ('div', True, {'class': 'tytul_oryg'}, None, None),
+    'miejsce_data': ('div', True, {'class': 'miejsce_data'}, None, None),
+    'audio': ('_ignore', False, None, None, None),
+    'www': ('a', True, {'class': 'www'}, {'href': '.text'}, False),
+
+    'tabela': ('table', False, None, None, None),
+    'tabelka': ('table', False, None, None, None),
+    'wiersz': ('tr', False, None, None, None),
+    'kol': ('td', True, None, None, None),
+
+    'ilustr': ('img', False, None, {'src': 'src'}, False),
+    'tab': ('span', False, {'class': 'tab'}, {'szer': 'szer'}, False),
+    
+}
+
+id_prefixes = {
+    'pa': 'fn',
+    'pe': 'fn',
+    'pr': 'fn',
+    'pt': 'fn',
+    'ptrad': 'fn',
+    'wers': 'f',
+    'wers_wciety': 'f',
+    'wers_cd': 'f',
+    'wers_akap': 'f',
+    'zastepnik_wersu': 'f',
+    'wers_do_prawej': 'f',
+    'wers_srodek': 'f',
+    'akap': 'f',
+    'akap_cd': 'f',
+    'akap_dialog': 'f',
 }
 
 
@@ -102,7 +158,7 @@ front2 = set(['autor_utworu'])
 
 
 def norm(text):
-    text = text.replace('---', '—').replace('--', '–').replace('...', '…').replace(',,', '„').replace('"', '”')
+    text = text.replace('---', '—').replace('--', '–').replace('...', '…').replace(',,', '„').replace('"', '”').replace('\n', ' ')
     return text
 
 
@@ -124,12 +180,21 @@ def toj(elem, S):
             if 'dlugi_cytat' not in S['stack'] and 'poezja_cyt' not in S['stack']:
                 S['vindex'] += 1
                 output['visibleNumber'] = S['vindex']
+        id_prefix = id_prefixes.get(elem.tag, 'i')
+        S['id'][id_prefix] += 1
+        output['id'] = id_prefix + str(S['id'][id_prefix])
+        if elem.attrib.get('id'):
+            output['id'] = 'wl-' + elem.attrib.get('id')
         if attrs:
             output['attr'] = attrs.copy()
         if attr_map:
             output.setdefault('attr', {})
             for k, v in attr_map.items():
-                output['attr'][k] = elem.attrib[v]
+                if v == '.text':
+                    val = elem.text
+                else:
+                    val = elem.attrib[v]
+                output['attr'][k] = val
         output['contents'] = contents
         output = [output]
     if elem.tag == 'strofa':
@@ -184,6 +249,7 @@ def conv(tree):
     S = {
         'index': 0,
         'vindex': 0,
+        'id': defaultdict(lambda: 0),
         'stack': [],
         'front1': [],
         'front2': [],