readme

README.md

@@ -4,4 +4,75 @@ tags:
 - endpoints-template
 license: bsd-3-clause
 library_name: generic
----
+---
+
+# Coreference Resolution for Long Documents
+Modified coreference resolution model from [BERT for Coreference Resolution: Baselines and Analysis](https://aclanthology.org/D19-1588/) for handling long documents (~40K words) efficiently (500K words/s on a NVIDIA Tesla V100). This modified model was used in [DAPR: A Benchmark on Document-Aware Passage Retrieval](https://arxiv.org/abs/2305.13915).
+
+## Usage
+### API call
+One can call the Hugging's Inference Endpoints API directly:
+```python
+import requests
+import time
+
+API_URL = "https://api-inference.huggingface.co/models/kwang2049/long-coref"
+headers = {"Authorization": "Bearer ${YOUR_HUGGINGFACE_ACCESS_TOKEN}"} 
+
+
+def query(payload):
+    while True:
+        response = requests.post(API_URL, headers=headers, json=payload)
+        if response.status_code == 503:
+            time.sleep(5)
+            print(response.json()["error"])
+            continue
+        elif response.status_code == 200:
+            return response.json()
+        else:
+            error_message = f"{response.status_code}: {response.json['error']}."
+            raise requests.HTTPError(error_message)
+
+
+doc = [
+    "The Half Moon is a public house and music venue in Putney, London. It is one of the city's longest running live music venues, and has hosted live music every night since 1963.",
+    "The pub is on the south side of the Lower Richmond road, in the London Borough of Wandsworth."
+]
+
+PARAGRAPH_DELIMITER = "\n\n"
+
+output = query(
+    {
+        "inputs": PARAGRAPH_DELIMITER.join(doc),
+    }
+)
+print(output)
+# {
+#     'pargraph_sentences': ..., 
+#     'top_spans': ..., 
+#     'antecedents': ...
+# }
+```
+### Local run
+One can also run the code of the repo on a local machine:
+
+```bash
+# Clone the repo
+git lfs install
+git clone https://huggingface.co/kwang2049/long-coref
+cd long-coref
+pip install -r requirements.txt
+python local_run.py
+```
+
+## Citation
+If you use the repo, feel free to cite our publication [DAPR: A Benchmark on Document-Aware Passage Retrieval](https://arxiv.org/abs/2305.13915):
+```bibtex 
+@article{wang2023dapr,
+    title = "DAPR: A Benchmark on Document-Aware Passage Retrieval",
+    author = "Kexin Wang and Nils Reimers and Iryna Gurevych", 
+    journal= "arXiv preprint arXiv:2305.13915",
+    year = "2023",
+    url = "https://arxiv.org/abs/2305.13915",
+}
+```

local_run.py

@@ -6,1891 +6,13 @@ my_handler = PreTrainedPipeline(path=".")
 doc = [
     "The Half Moon is a public house and music venue in Putney, London. It is one of the city's longest running live music venues, and has hosted live music every night since 1963.",
     "The pub is on the south side of the Lower Richmond road, in the London Borough of Wandsworth.",
-    "The Half Moon is one of London's longest running, and most respected live music venues. Since the early 1960s, some of the biggest names in popular music have performed there, including The Rolling Stones, and The Who. The venue has hosted live music every night since 1963.It all began with the folk and blues sessions started by Gerry Lockran, Royd Rivers and Cliff Aungier in 1963. 'Folksville', as the sessions were called, featured new British and European artists alongside established American blues-men. These included Sonny Terry and Brownie McGhee, Champion Jack Dupree and Arthur Crudup. British acts included Ralph McTell, John Martyn, Bert Jansch and Roy Harper.John Mayall's Bluesbreakers, Alexis Korner, and The Yardbirds made an appearance here and at other South London venues such as The Eel Pie Club and Crawdaddy Club.As blues and folk thrived, bringing Fairport Convention and Van Morrison, so other genres began to appear. From the psychedelia of The Bonzo Dog Doo Dah Band and Bob Kerr's Whoopee Band; to 1960s mod groups The Pretty Things and Nashville Teens; to early pub-rock acts such as Dr. Feelgood; the Half Moon was the centre of not only the emerging music scenes but continued to host the big names.It was never just a \"passing through\" venue. Residencies at the Half Moon have included Elvis Costello (who would play a couple of times a month in the mid-1970s for 50 pence and a plate of sandwiches) and Steve Marriott of Small Faces fame. John Martyn returned decades after his first Half Moon gigs to a week-long residency, and both Tim Rose and Roy Harper did the same.  On 24 July 2007, Welsh-language folk guitarist Meic Stevens performed his first London gig in over 30 years at the Half Moon.  Other memorable gigs at the Half Moon include k.d. lang's first UK appearance, Kate Bush's first ever public performance and a surprise appearance by Nick Cave. The Hamsters played their last shows at the Half Moon in 2012, signing off on a 25-year career with five shows over one weekend.The Half Moon has always been synonymous with The Rolling Stones, whose most recent visit was a private event held in May 2000. As well as performing as the band, individual members have appeared here in various side-projects, and have also used the venue for rehearsal space. In January 2010, the Half Moon almost closed due to failing sales, rising rates and the recession, but they received hundreds of signatures and a Facebook campaign of 6,500 people. Musicians such as The X Factor finalist Jamie Archer, Eddi Reader and Simon Fowler supported the petition as well. As part of its revival, the Half Moon started serving food.In 2012, the Half Moon was bought by Geronimo Inns, whose parent company is Young & Co.",
-    "Artists who have performed or recorded at the venue since the mid-1960s include the Rolling Stones, The Who, The Small Faces, Kasabian, Sisteray, Chris Bell, Ralph McTell, GoodLuck, John Martyn, John Mayall's Bluesbreakers, Alexis Korner, The Yardbirds, Bob Kerr's Whoopee Band, Morrissey–Mullen – who had a residency there of several years' standing, Rocket 88, Fairport Convention, Bonzo Dog Doo-Dah Band, Roy Harper, Van Morrison,Man, Danny Thompson, Dr. Feelgood, Elvis Costello, Meic Stevens, Finley Quaye, I Am Kloot, Starlite Campbell Band, Beverley Craven, Bo Diddley, John Otway, Tim Rose, Amy McDonald, Catfish Keith, The MonaLisa Twins, as well as k.d. lang's first UK appearance, and Kate Bush's first public performance.It has also hosted comedy, including Billy Connolly, Andy Parsons, Harry Hill, Rufus Hound, Shappi Khorsandi, Norman Lovett, Bob Mills, Milton Jones, Al Murray, Stewart Lee, Richard Herring, Jack Whitehall, Alistair McGowan, Katherine Ryan, Cardinal Burns, Reginald D. Hunter, Stewart Francis, Bridget Christie, Josh Widdicombe, Sara Pascoe, Rob Beckett, Sean Hughes, Kevin Eldon, Henning Wehn, Hal Cruttenden, Holly Walsh, Danny Bhoy, Aisling Bea and James Acaster.",
-    "Live at Half Moon Putney – The De Luxe Blues Band (1981)An Evening with Meic Stevens: Recorded Live in London – Meic Stevens (2007) (Sunbeam Records, SBRCD5033)Live at the Half Moon – Catfish Keith (2009) (Fish Tail Records)Remember, on stage at The Half Moon – Latin Quarter (2023) (Westpark Music)",
-    "The pub is served by Transport for London buses 22, 265, 378, 485 which stop on the Lower Richmond road. Putney Bridge tube station (District line) is a 12 minute walk over Putney Bridge and Putney railway station (Southwestern Railway) is a 12 minute walk up Putney High Street.The Santander Cycles Putney Pier docking station is a three minute walk.",
-    "Official website",
 ]
-doc_string = "\n\n".join(doc)
+PARAGRAPH_DELIMITER = "\n\n"
+doc_string = PARAGRAPH_DELIMITER.join(doc)
 
 # prepare sample payload
-payload = {"inputs": doc_string}
+payload = doc_string
 prediction = my_handler(payload)
 
 # show results
 print(prediction)
-
-# {
-#     "pargraph_sentences": [
-#         [
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "public", "text_with_ws": "public "},
-#                 {"text": "house", "text_with_ws": "house "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "venue", "text_with_ws": "venue "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "Putney", "text_with_ws": "Putney"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "London", "text_with_ws": "London"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "It", "text_with_ws": "It "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "one", "text_with_ws": "one "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "city", "text_with_ws": "city"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "longest", "text_with_ws": "longest "},
-#                 {"text": "running", "text_with_ws": "running "},
-#                 {"text": "live", "text_with_ws": "live "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "venues", "text_with_ws": "venues"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "has", "text_with_ws": "has "},
-#                 {"text": "hosted", "text_with_ws": "hosted "},
-#                 {"text": "live", "text_with_ws": "live "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "every", "text_with_ws": "every "},
-#                 {"text": "night", "text_with_ws": "night "},
-#                 {"text": "since", "text_with_ws": "since "},
-#                 {"text": "1963", "text_with_ws": "1963"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#         ],
-#         [
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "pub", "text_with_ws": "pub "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "on", "text_with_ws": "on "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "south", "text_with_ws": "south "},
-#                 {"text": "side", "text_with_ws": "side "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Lower", "text_with_ws": "Lower "},
-#                 {"text": "Richmond", "text_with_ws": "Richmond "},
-#                 {"text": "road", "text_with_ws": "road"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "London", "text_with_ws": "London "},
-#                 {"text": "Borough", "text_with_ws": "Borough "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "Wandsworth", "text_with_ws": "Wandsworth"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ]
-#         ],
-#         [
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "one", "text_with_ws": "one "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "London", "text_with_ws": "London"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "longest", "text_with_ws": "longest "},
-#                 {"text": "running", "text_with_ws": "running"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "most", "text_with_ws": "most "},
-#                 {"text": "respected", "text_with_ws": "respected "},
-#                 {"text": "live", "text_with_ws": "live "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "venues", "text_with_ws": "venues"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "Since", "text_with_ws": "Since "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "early", "text_with_ws": "early "},
-#                 {"text": "1960s", "text_with_ws": "1960s"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "some", "text_with_ws": "some "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "biggest", "text_with_ws": "biggest "},
-#                 {"text": "names", "text_with_ws": "names "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "popular", "text_with_ws": "popular "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "have", "text_with_ws": "have "},
-#                 {"text": "performed", "text_with_ws": "performed "},
-#                 {"text": "there", "text_with_ws": "there"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "including", "text_with_ws": "including "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Rolling", "text_with_ws": "Rolling "},
-#                 {"text": "Stones", "text_with_ws": "Stones"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Who", "text_with_ws": "Who"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "venue", "text_with_ws": "venue "},
-#                 {"text": "has", "text_with_ws": "has "},
-#                 {"text": "hosted", "text_with_ws": "hosted "},
-#                 {"text": "live", "text_with_ws": "live "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "every", "text_with_ws": "every "},
-#                 {"text": "night", "text_with_ws": "night "},
-#                 {"text": "since", "text_with_ws": "since "},
-#                 {"text": "1963.It", "text_with_ws": "1963.It "},
-#                 {"text": "all", "text_with_ws": "all "},
-#                 {"text": "began", "text_with_ws": "began "},
-#                 {"text": "with", "text_with_ws": "with "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "folk", "text_with_ws": "folk "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "blues", "text_with_ws": "blues "},
-#                 {"text": "sessions", "text_with_ws": "sessions "},
-#                 {"text": "started", "text_with_ws": "started "},
-#                 {"text": "by", "text_with_ws": "by "},
-#                 {"text": "Gerry", "text_with_ws": "Gerry "},
-#                 {"text": "Lockran", "text_with_ws": "Lockran"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Royd", "text_with_ws": "Royd "},
-#                 {"text": "Rivers", "text_with_ws": "Rivers "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Cliff", "text_with_ws": "Cliff "},
-#                 {"text": "Aungier", "text_with_ws": "Aungier "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "1963", "text_with_ws": "1963"},
-#                 {"text": ".", "text_with_ws": ". "},
-#                 {"text": "'", "text_with_ws": "'"},
-#             ],
-#             [
-#                 {"text": "Folksville", "text_with_ws": "Folksville"},
-#                 {"text": "'", "text_with_ws": "'"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "sessions", "text_with_ws": "sessions "},
-#                 {"text": "were", "text_with_ws": "were "},
-#                 {"text": "called", "text_with_ws": "called"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "featured", "text_with_ws": "featured "},
-#                 {"text": "new", "text_with_ws": "new "},
-#                 {"text": "British", "text_with_ws": "British "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "European", "text_with_ws": "European "},
-#                 {"text": "artists", "text_with_ws": "artists "},
-#                 {"text": "alongside", "text_with_ws": "alongside "},
-#                 {"text": "established", "text_with_ws": "established "},
-#                 {"text": "American", "text_with_ws": "American "},
-#                 {"text": "blues", "text_with_ws": "blues"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "men", "text_with_ws": "men"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "These", "text_with_ws": "These "},
-#                 {"text": "included", "text_with_ws": "included "},
-#                 {"text": "Sonny", "text_with_ws": "Sonny "},
-#                 {"text": "Terry", "text_with_ws": "Terry "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Brownie", "text_with_ws": "Brownie "},
-#                 {"text": "McGhee", "text_with_ws": "McGhee"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Champion", "text_with_ws": "Champion "},
-#                 {"text": "Jack", "text_with_ws": "Jack "},
-#                 {"text": "Dupree", "text_with_ws": "Dupree "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Arthur", "text_with_ws": "Arthur "},
-#                 {"text": "Crudup", "text_with_ws": "Crudup"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "British", "text_with_ws": "British "},
-#                 {"text": "acts", "text_with_ws": "acts "},
-#                 {"text": "included", "text_with_ws": "included "},
-#                 {"text": "Ralph", "text_with_ws": "Ralph "},
-#                 {"text": "McTell", "text_with_ws": "McTell"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "John", "text_with_ws": "John "},
-#                 {"text": "Martyn", "text_with_ws": "Martyn"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Bert", "text_with_ws": "Bert "},
-#                 {"text": "Jansch", "text_with_ws": "Jansch "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Roy", "text_with_ws": "Roy "},
-#                 {"text": "Harper", "text_with_ws": "Harper"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "John", "text_with_ws": "John "},
-#                 {"text": "Mayall", "text_with_ws": "Mayall"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "Bluesbreakers", "text_with_ws": "Bluesbreakers"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Alexis", "text_with_ws": "Alexis "},
-#                 {"text": "Korner", "text_with_ws": "Korner"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Yardbirds", "text_with_ws": "Yardbirds "},
-#                 {"text": "made", "text_with_ws": "made "},
-#                 {"text": "an", "text_with_ws": "an "},
-#                 {"text": "appearance", "text_with_ws": "appearance "},
-#                 {"text": "here", "text_with_ws": "here "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "other", "text_with_ws": "other "},
-#                 {"text": "South", "text_with_ws": "South "},
-#                 {"text": "London", "text_with_ws": "London "},
-#                 {"text": "venues", "text_with_ws": "venues "},
-#                 {"text": "such", "text_with_ws": "such "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Eel", "text_with_ws": "Eel "},
-#                 {"text": "Pie", "text_with_ws": "Pie "},
-#                 {"text": "Club", "text_with_ws": "Club "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Crawdaddy", "text_with_ws": "Crawdaddy "},
-#                 {"text": "Club", "text_with_ws": "Club"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "As", "text_with_ws": "As "},
-#                 {"text": "blues", "text_with_ws": "blues "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "folk", "text_with_ws": "folk "},
-#                 {"text": "thrived", "text_with_ws": "thrived"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "bringing", "text_with_ws": "bringing "},
-#                 {"text": "Fairport", "text_with_ws": "Fairport "},
-#                 {"text": "Convention", "text_with_ws": "Convention "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Van", "text_with_ws": "Van "},
-#                 {"text": "Morrison", "text_with_ws": "Morrison"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "so", "text_with_ws": "so "},
-#                 {"text": "other", "text_with_ws": "other "},
-#                 {"text": "genres", "text_with_ws": "genres "},
-#                 {"text": "began", "text_with_ws": "began "},
-#                 {"text": "to", "text_with_ws": "to "},
-#                 {"text": "appear", "text_with_ws": "appear"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "From", "text_with_ws": "From "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "psychedelia", "text_with_ws": "psychedelia "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Bonzo", "text_with_ws": "Bonzo "},
-#                 {"text": "Dog", "text_with_ws": "Dog "},
-#                 {"text": "Doo", "text_with_ws": "Doo "},
-#                 {"text": "Dah", "text_with_ws": "Dah "},
-#                 {"text": "Band", "text_with_ws": "Band "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Bob", "text_with_ws": "Bob "},
-#                 {"text": "Kerr", "text_with_ws": "Kerr"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "Whoopee", "text_with_ws": "Whoopee "},
-#                 {"text": "Band", "text_with_ws": "Band"},
-#                 {"text": ";", "text_with_ws": "; "},
-#                 {"text": "to", "text_with_ws": "to "},
-#                 {"text": "1960s", "text_with_ws": "1960s "},
-#                 {"text": "mod", "text_with_ws": "mod "},
-#                 {"text": "groups", "text_with_ws": "groups "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Pretty", "text_with_ws": "Pretty "},
-#                 {"text": "Things", "text_with_ws": "Things "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Nashville", "text_with_ws": "Nashville "},
-#                 {"text": "Teens", "text_with_ws": "Teens"},
-#                 {"text": ";", "text_with_ws": "; "},
-#                 {"text": "to", "text_with_ws": "to "},
-#                 {"text": "early", "text_with_ws": "early "},
-#                 {"text": "pub", "text_with_ws": "pub"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "rock", "text_with_ws": "rock "},
-#                 {"text": "acts", "text_with_ws": "acts "},
-#                 {"text": "such", "text_with_ws": "such "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "Dr.", "text_with_ws": "Dr. "},
-#                 {"text": "Feelgood", "text_with_ws": "Feelgood"},
-#                 {"text": ";", "text_with_ws": "; "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "was", "text_with_ws": "was "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "centre", "text_with_ws": "centre "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "not", "text_with_ws": "not "},
-#                 {"text": "only", "text_with_ws": "only "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "emerging", "text_with_ws": "emerging "},
-#                 {"text": "music", "text_with_ws": "music "},
-#                 {"text": "scenes", "text_with_ws": "scenes "},
-#                 {"text": "but", "text_with_ws": "but "},
-#                 {"text": "continued", "text_with_ws": "continued "},
-#                 {"text": "to", "text_with_ws": "to "},
-#                 {"text": "host", "text_with_ws": "host "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "big", "text_with_ws": "big "},
-#                 {"text": "names", "text_with_ws": "names"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "It", "text_with_ws": "It "},
-#                 {"text": "was", "text_with_ws": "was "},
-#                 {"text": "never", "text_with_ws": "never "},
-#                 {"text": "just", "text_with_ws": "just "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": '"', "text_with_ws": '"'},
-#                 {"text": "passing", "text_with_ws": "passing "},
-#                 {"text": "through", "text_with_ws": "through"},
-#                 {"text": '"', "text_with_ws": '" '},
-#                 {"text": "venue", "text_with_ws": "venue"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "Residencies", "text_with_ws": "Residencies "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "have", "text_with_ws": "have "},
-#                 {"text": "included", "text_with_ws": "included "},
-#                 {"text": "Elvis", "text_with_ws": "Elvis "},
-#                 {"text": "Costello", "text_with_ws": "Costello "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "who", "text_with_ws": "who "},
-#                 {"text": "would", "text_with_ws": "would "},
-#                 {"text": "play", "text_with_ws": "play "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "couple", "text_with_ws": "couple "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "times", "text_with_ws": "times "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "month", "text_with_ws": "month "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "mid-1970s", "text_with_ws": "mid-1970s "},
-#                 {"text": "for", "text_with_ws": "for "},
-#                 {"text": "50", "text_with_ws": "50 "},
-#                 {"text": "pence", "text_with_ws": "pence "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "plate", "text_with_ws": "plate "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "sandwiches", "text_with_ws": "sandwiches"},
-#                 {"text": ")", "text_with_ws": ") "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Steve", "text_with_ws": "Steve "},
-#                 {"text": "Marriott", "text_with_ws": "Marriott "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "Small", "text_with_ws": "Small "},
-#                 {"text": "Faces", "text_with_ws": "Faces "},
-#                 {"text": "fame", "text_with_ws": "fame"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "John", "text_with_ws": "John "},
-#                 {"text": "Martyn", "text_with_ws": "Martyn "},
-#                 {"text": "returned", "text_with_ws": "returned "},
-#                 {"text": "decades", "text_with_ws": "decades "},
-#                 {"text": "after", "text_with_ws": "after "},
-#                 {"text": "his", "text_with_ws": "his "},
-#                 {"text": "first", "text_with_ws": "first "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "gigs", "text_with_ws": "gigs "},
-#                 {"text": "to", "text_with_ws": "to "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "week", "text_with_ws": "week"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "long", "text_with_ws": "long "},
-#                 {"text": "residency", "text_with_ws": "residency"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "both", "text_with_ws": "both "},
-#                 {"text": "Tim", "text_with_ws": "Tim "},
-#                 {"text": "Rose", "text_with_ws": "Rose "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Roy", "text_with_ws": "Roy "},
-#                 {"text": "Harper", "text_with_ws": "Harper "},
-#                 {"text": "did", "text_with_ws": "did "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "same", "text_with_ws": "same"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": " ", "text_with_ws": " "},
-#                 {"text": "On", "text_with_ws": "On "},
-#                 {"text": "24", "text_with_ws": "24 "},
-#                 {"text": "July", "text_with_ws": "July "},
-#                 {"text": "2007", "text_with_ws": "2007"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Welsh", "text_with_ws": "Welsh"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "language", "text_with_ws": "language "},
-#                 {"text": "folk", "text_with_ws": "folk "},
-#                 {"text": "guitarist", "text_with_ws": "guitarist "},
-#                 {"text": "Meic", "text_with_ws": "Meic "},
-#                 {"text": "Stevens", "text_with_ws": "Stevens "},
-#                 {"text": "performed", "text_with_ws": "performed "},
-#                 {"text": "his", "text_with_ws": "his "},
-#                 {"text": "first", "text_with_ws": "first "},
-#                 {"text": "London", "text_with_ws": "London "},
-#                 {"text": "gig", "text_with_ws": "gig "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "over", "text_with_ws": "over "},
-#                 {"text": "30", "text_with_ws": "30 "},
-#                 {"text": "years", "text_with_ws": "years "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": " ", "text_with_ws": " "},
-#                 {"text": "Other", "text_with_ws": "Other "},
-#                 {"text": "memorable", "text_with_ws": "memorable "},
-#                 {"text": "gigs", "text_with_ws": "gigs "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "include", "text_with_ws": "include "},
-#                 {"text": "k.d", "text_with_ws": "k.d"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "lang", "text_with_ws": "lang"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "first", "text_with_ws": "first "},
-#                 {"text": "UK", "text_with_ws": "UK "},
-#                 {"text": "appearance", "text_with_ws": "appearance"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Kate", "text_with_ws": "Kate "},
-#                 {"text": "Bush", "text_with_ws": "Bush"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "first", "text_with_ws": "first "},
-#                 {"text": "ever", "text_with_ws": "ever "},
-#                 {"text": "public", "text_with_ws": "public "},
-#                 {"text": "performance", "text_with_ws": "performance "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "surprise", "text_with_ws": "surprise "},
-#                 {"text": "appearance", "text_with_ws": "appearance "},
-#                 {"text": "by", "text_with_ws": "by "},
-#                 {"text": "Nick", "text_with_ws": "Nick "},
-#                 {"text": "Cave", "text_with_ws": "Cave"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Hamsters", "text_with_ws": "Hamsters "},
-#                 {"text": "played", "text_with_ws": "played "},
-#                 {"text": "their", "text_with_ws": "their "},
-#                 {"text": "last", "text_with_ws": "last "},
-#                 {"text": "shows", "text_with_ws": "shows "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "2012", "text_with_ws": "2012"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "signing", "text_with_ws": "signing "},
-#                 {"text": "off", "text_with_ws": "off "},
-#                 {"text": "on", "text_with_ws": "on "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "25", "text_with_ws": "25"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "year", "text_with_ws": "year "},
-#                 {"text": "career", "text_with_ws": "career "},
-#                 {"text": "with", "text_with_ws": "with "},
-#                 {"text": "five", "text_with_ws": "five "},
-#                 {"text": "shows", "text_with_ws": "shows "},
-#                 {"text": "over", "text_with_ws": "over "},
-#                 {"text": "one", "text_with_ws": "one "},
-#                 {"text": "weekend", "text_with_ws": "weekend"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "has", "text_with_ws": "has "},
-#                 {"text": "always", "text_with_ws": "always "},
-#                 {"text": "been", "text_with_ws": "been "},
-#                 {"text": "synonymous", "text_with_ws": "synonymous "},
-#                 {"text": "with", "text_with_ws": "with "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Rolling", "text_with_ws": "Rolling "},
-#                 {"text": "Stones", "text_with_ws": "Stones"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "whose", "text_with_ws": "whose "},
-#                 {"text": "most", "text_with_ws": "most "},
-#                 {"text": "recent", "text_with_ws": "recent "},
-#                 {"text": "visit", "text_with_ws": "visit "},
-#                 {"text": "was", "text_with_ws": "was "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "private", "text_with_ws": "private "},
-#                 {"text": "event", "text_with_ws": "event "},
-#                 {"text": "held", "text_with_ws": "held "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "May", "text_with_ws": "May "},
-#                 {"text": "2000", "text_with_ws": "2000"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "As", "text_with_ws": "As "},
-#                 {"text": "well", "text_with_ws": "well "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "performing", "text_with_ws": "performing "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "band", "text_with_ws": "band"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "individual", "text_with_ws": "individual "},
-#                 {"text": "members", "text_with_ws": "members "},
-#                 {"text": "have", "text_with_ws": "have "},
-#                 {"text": "appeared", "text_with_ws": "appeared "},
-#                 {"text": "here", "text_with_ws": "here "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "various", "text_with_ws": "various "},
-#                 {"text": "side", "text_with_ws": "side"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "projects", "text_with_ws": "projects"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "have", "text_with_ws": "have "},
-#                 {"text": "also", "text_with_ws": "also "},
-#                 {"text": "used", "text_with_ws": "used "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "venue", "text_with_ws": "venue "},
-#                 {"text": "for", "text_with_ws": "for "},
-#                 {"text": "rehearsal", "text_with_ws": "rehearsal "},
-#                 {"text": "space", "text_with_ws": "space"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "In", "text_with_ws": "In "},
-#                 {"text": "January", "text_with_ws": "January "},
-#                 {"text": "2010", "text_with_ws": "2010"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "almost", "text_with_ws": "almost "},
-#                 {"text": "closed", "text_with_ws": "closed "},
-#                 {"text": "due", "text_with_ws": "due "},
-#                 {"text": "to", "text_with_ws": "to "},
-#                 {"text": "failing", "text_with_ws": "failing "},
-#                 {"text": "sales", "text_with_ws": "sales"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "rising", "text_with_ws": "rising "},
-#                 {"text": "rates", "text_with_ws": "rates "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "recession", "text_with_ws": "recession"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "but", "text_with_ws": "but "},
-#                 {"text": "they", "text_with_ws": "they "},
-#                 {"text": "received", "text_with_ws": "received "},
-#                 {"text": "hundreds", "text_with_ws": "hundreds "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "signatures", "text_with_ws": "signatures "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "Facebook", "text_with_ws": "Facebook "},
-#                 {"text": "campaign", "text_with_ws": "campaign "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "6,500", "text_with_ws": "6,500 "},
-#                 {"text": "people", "text_with_ws": "people"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "Musicians", "text_with_ws": "Musicians "},
-#                 {"text": "such", "text_with_ws": "such "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "X", "text_with_ws": "X "},
-#                 {"text": "Factor", "text_with_ws": "Factor "},
-#                 {"text": "finalist", "text_with_ws": "finalist "},
-#                 {"text": "Jamie", "text_with_ws": "Jamie "},
-#                 {"text": "Archer", "text_with_ws": "Archer"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Eddi", "text_with_ws": "Eddi "},
-#                 {"text": "Reader", "text_with_ws": "Reader "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Simon", "text_with_ws": "Simon "},
-#                 {"text": "Fowler", "text_with_ws": "Fowler "},
-#                 {"text": "supported", "text_with_ws": "supported "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "petition", "text_with_ws": "petition "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "well", "text_with_ws": "well"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "As", "text_with_ws": "As "},
-#                 {"text": "part", "text_with_ws": "part "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "its", "text_with_ws": "its "},
-#                 {"text": "revival", "text_with_ws": "revival"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "started", "text_with_ws": "started "},
-#                 {"text": "serving", "text_with_ws": "serving "},
-#                 {"text": "food", "text_with_ws": "food"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "In", "text_with_ws": "In "},
-#                 {"text": "2012", "text_with_ws": "2012"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "was", "text_with_ws": "was "},
-#                 {"text": "bought", "text_with_ws": "bought "},
-#                 {"text": "by", "text_with_ws": "by "},
-#                 {"text": "Geronimo", "text_with_ws": "Geronimo "},
-#                 {"text": "Inns", "text_with_ws": "Inns"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "whose", "text_with_ws": "whose "},
-#                 {"text": "parent", "text_with_ws": "parent "},
-#                 {"text": "company", "text_with_ws": "company "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "Young", "text_with_ws": "Young "},
-#                 {"text": "&", "text_with_ws": "& "},
-#                 {"text": "Co.", "text_with_ws": "Co."},
-#             ],
-#         ],
-#         [
-#             [
-#                 {"text": "Artists", "text_with_ws": "Artists "},
-#                 {"text": "who", "text_with_ws": "who "},
-#                 {"text": "have", "text_with_ws": "have "},
-#                 {"text": "performed", "text_with_ws": "performed "},
-#                 {"text": "or", "text_with_ws": "or "},
-#                 {"text": "recorded", "text_with_ws": "recorded "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "venue", "text_with_ws": "venue "},
-#                 {"text": "since", "text_with_ws": "since "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "mid-1960s", "text_with_ws": "mid-1960s "},
-#                 {"text": "include", "text_with_ws": "include "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Rolling", "text_with_ws": "Rolling "},
-#                 {"text": "Stones", "text_with_ws": "Stones"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Who", "text_with_ws": "Who"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Small", "text_with_ws": "Small "},
-#                 {"text": "Faces", "text_with_ws": "Faces"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Kasabian", "text_with_ws": "Kasabian"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Sisteray", "text_with_ws": "Sisteray"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Chris", "text_with_ws": "Chris "},
-#                 {"text": "Bell", "text_with_ws": "Bell"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Ralph", "text_with_ws": "Ralph "},
-#                 {"text": "McTell", "text_with_ws": "McTell"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "GoodLuck", "text_with_ws": "GoodLuck"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "John", "text_with_ws": "John "},
-#                 {"text": "Martyn", "text_with_ws": "Martyn"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "John", "text_with_ws": "John "},
-#                 {"text": "Mayall", "text_with_ws": "Mayall"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "Bluesbreakers", "text_with_ws": "Bluesbreakers"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Alexis", "text_with_ws": "Alexis "},
-#                 {"text": "Korner", "text_with_ws": "Korner"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Yardbirds", "text_with_ws": "Yardbirds"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Bob", "text_with_ws": "Bob "},
-#                 {"text": "Kerr", "text_with_ws": "Kerr"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "Whoopee", "text_with_ws": "Whoopee "},
-#                 {"text": "Band", "text_with_ws": "Band"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Morrissey", "text_with_ws": "Morrissey"},
-#                 {"text": "–", "text_with_ws": "–"},
-#                 {"text": "Mullen", "text_with_ws": "Mullen "},
-#                 {"text": "–", "text_with_ws": "– "},
-#                 {"text": "who", "text_with_ws": "who "},
-#                 {"text": "had", "text_with_ws": "had "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "residency", "text_with_ws": "residency "},
-#                 {"text": "there", "text_with_ws": "there "},
-#                 {"text": "of", "text_with_ws": "of "},
-#                 {"text": "several", "text_with_ws": "several "},
-#                 {"text": "years", "text_with_ws": "years"},
-#                 {"text": "'", "text_with_ws": "' "},
-#                 {"text": "standing", "text_with_ws": "standing"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Rocket", "text_with_ws": "Rocket "},
-#                 {"text": "88", "text_with_ws": "88"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Fairport", "text_with_ws": "Fairport "},
-#                 {"text": "Convention", "text_with_ws": "Convention"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Bonzo", "text_with_ws": "Bonzo "},
-#                 {"text": "Dog", "text_with_ws": "Dog "},
-#                 {"text": "Doo", "text_with_ws": "Doo"},
-#                 {"text": "-", "text_with_ws": "-"},
-#                 {"text": "Dah", "text_with_ws": "Dah "},
-#                 {"text": "Band", "text_with_ws": "Band"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Roy", "text_with_ws": "Roy "},
-#                 {"text": "Harper", "text_with_ws": "Harper"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Van", "text_with_ws": "Van "},
-#                 {"text": "Morrison", "text_with_ws": "Morrison"},
-#                 {"text": ",", "text_with_ws": ","},
-#                 {"text": "Man", "text_with_ws": "Man"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Danny", "text_with_ws": "Danny "},
-#                 {"text": "Thompson", "text_with_ws": "Thompson"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Dr.", "text_with_ws": "Dr. "},
-#                 {"text": "Feelgood", "text_with_ws": "Feelgood"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Elvis", "text_with_ws": "Elvis "},
-#                 {"text": "Costello", "text_with_ws": "Costello"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Meic", "text_with_ws": "Meic "},
-#                 {"text": "Stevens", "text_with_ws": "Stevens"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Finley", "text_with_ws": "Finley "},
-#                 {"text": "Quaye", "text_with_ws": "Quaye"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "I", "text_with_ws": "I "},
-#                 {"text": "Am", "text_with_ws": "Am "},
-#                 {"text": "Kloot", "text_with_ws": "Kloot"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Starlite", "text_with_ws": "Starlite "},
-#                 {"text": "Campbell", "text_with_ws": "Campbell "},
-#                 {"text": "Band", "text_with_ws": "Band"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Beverley", "text_with_ws": "Beverley "},
-#                 {"text": "Craven", "text_with_ws": "Craven"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Bo", "text_with_ws": "Bo "},
-#                 {"text": "Diddley", "text_with_ws": "Diddley"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "John", "text_with_ws": "John "},
-#                 {"text": "Otway", "text_with_ws": "Otway"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Tim", "text_with_ws": "Tim "},
-#                 {"text": "Rose", "text_with_ws": "Rose"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Amy", "text_with_ws": "Amy "},
-#                 {"text": "McDonald", "text_with_ws": "McDonald"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Catfish", "text_with_ws": "Catfish "},
-#                 {"text": "Keith", "text_with_ws": "Keith"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "MonaLisa", "text_with_ws": "MonaLisa "},
-#                 {"text": "Twins", "text_with_ws": "Twins"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "well", "text_with_ws": "well "},
-#                 {"text": "as", "text_with_ws": "as "},
-#                 {"text": "k.d", "text_with_ws": "k.d"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "lang", "text_with_ws": "lang"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "first", "text_with_ws": "first "},
-#                 {"text": "UK", "text_with_ws": "UK "},
-#                 {"text": "appearance", "text_with_ws": "appearance"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Kate", "text_with_ws": "Kate "},
-#                 {"text": "Bush", "text_with_ws": "Bush"},
-#                 {"text": "'s", "text_with_ws": "'s "},
-#                 {"text": "first", "text_with_ws": "first "},
-#                 {"text": "public", "text_with_ws": "public "},
-#                 {"text": "performance", "text_with_ws": "performance"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "It", "text_with_ws": "It "},
-#                 {"text": "has", "text_with_ws": "has "},
-#                 {"text": "also", "text_with_ws": "also "},
-#                 {"text": "hosted", "text_with_ws": "hosted "},
-#                 {"text": "comedy", "text_with_ws": "comedy"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "including", "text_with_ws": "including "},
-#                 {"text": "Billy", "text_with_ws": "Billy "},
-#                 {"text": "Connolly", "text_with_ws": "Connolly"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Andy", "text_with_ws": "Andy "},
-#                 {"text": "Parsons", "text_with_ws": "Parsons"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Harry", "text_with_ws": "Harry "},
-#                 {"text": "Hill", "text_with_ws": "Hill"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Rufus", "text_with_ws": "Rufus "},
-#                 {"text": "Hound", "text_with_ws": "Hound"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Shappi", "text_with_ws": "Shappi "},
-#                 {"text": "Khorsandi", "text_with_ws": "Khorsandi"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Norman", "text_with_ws": "Norman "},
-#                 {"text": "Lovett", "text_with_ws": "Lovett"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Bob", "text_with_ws": "Bob "},
-#                 {"text": "Mills", "text_with_ws": "Mills"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Milton", "text_with_ws": "Milton "},
-#                 {"text": "Jones", "text_with_ws": "Jones"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Al", "text_with_ws": "Al "},
-#                 {"text": "Murray", "text_with_ws": "Murray"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Stewart", "text_with_ws": "Stewart "},
-#                 {"text": "Lee", "text_with_ws": "Lee"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Richard", "text_with_ws": "Richard "},
-#                 {"text": "Herring", "text_with_ws": "Herring"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Jack", "text_with_ws": "Jack "},
-#                 {"text": "Whitehall", "text_with_ws": "Whitehall"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Alistair", "text_with_ws": "Alistair "},
-#                 {"text": "McGowan", "text_with_ws": "McGowan"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Katherine", "text_with_ws": "Katherine "},
-#                 {"text": "Ryan", "text_with_ws": "Ryan"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Cardinal", "text_with_ws": "Cardinal "},
-#                 {"text": "Burns", "text_with_ws": "Burns"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Reginald", "text_with_ws": "Reginald "},
-#                 {"text": "D.", "text_with_ws": "D. "},
-#                 {"text": "Hunter", "text_with_ws": "Hunter"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Stewart", "text_with_ws": "Stewart "},
-#                 {"text": "Francis", "text_with_ws": "Francis"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Bridget", "text_with_ws": "Bridget "},
-#                 {"text": "Christie", "text_with_ws": "Christie"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Josh", "text_with_ws": "Josh "},
-#                 {"text": "Widdicombe", "text_with_ws": "Widdicombe"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Sara", "text_with_ws": "Sara "},
-#                 {"text": "Pascoe", "text_with_ws": "Pascoe"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Rob", "text_with_ws": "Rob "},
-#                 {"text": "Beckett", "text_with_ws": "Beckett"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Sean", "text_with_ws": "Sean "},
-#                 {"text": "Hughes", "text_with_ws": "Hughes"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Kevin", "text_with_ws": "Kevin "},
-#                 {"text": "Eldon", "text_with_ws": "Eldon"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Henning", "text_with_ws": "Henning "},
-#                 {"text": "Wehn", "text_with_ws": "Wehn"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Hal", "text_with_ws": "Hal "},
-#                 {"text": "Cruttenden", "text_with_ws": "Cruttenden"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Holly", "text_with_ws": "Holly "},
-#                 {"text": "Walsh", "text_with_ws": "Walsh"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Danny", "text_with_ws": "Danny "},
-#                 {"text": "Bhoy", "text_with_ws": "Bhoy"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "Aisling", "text_with_ws": "Aisling "},
-#                 {"text": "Bea", "text_with_ws": "Bea "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "James", "text_with_ws": "James "},
-#                 {"text": "Acaster", "text_with_ws": "Acaster"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#         ],
-#         [
-#             [
-#                 {"text": "Live", "text_with_ws": "Live "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "Putney", "text_with_ws": "Putney "},
-#                 {"text": "–", "text_with_ws": "– "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "De", "text_with_ws": "De "},
-#                 {"text": "Luxe", "text_with_ws": "Luxe "},
-#                 {"text": "Blues", "text_with_ws": "Blues "},
-#                 {"text": "Band", "text_with_ws": "Band "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "1981)An", "text_with_ws": "1981)An "},
-#                 {"text": "Evening", "text_with_ws": "Evening "},
-#                 {"text": "with", "text_with_ws": "with "},
-#                 {"text": "Meic", "text_with_ws": "Meic "},
-#                 {"text": "Stevens", "text_with_ws": "Stevens"},
-#                 {"text": ":", "text_with_ws": ": "},
-#                 {"text": "Recorded", "text_with_ws": "Recorded "},
-#                 {"text": "Live", "text_with_ws": "Live "},
-#                 {"text": "in", "text_with_ws": "in "},
-#                 {"text": "London", "text_with_ws": "London "},
-#                 {"text": "–", "text_with_ws": "– "},
-#                 {"text": "Meic", "text_with_ws": "Meic "},
-#                 {"text": "Stevens", "text_with_ws": "Stevens "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "2007", "text_with_ws": "2007"},
-#                 {"text": ")", "text_with_ws": ") "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "Sunbeam", "text_with_ws": "Sunbeam "},
-#                 {"text": "Records", "text_with_ws": "Records"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "SBRCD5033)Live", "text_with_ws": "SBRCD5033)Live "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "–", "text_with_ws": "– "},
-#                 {"text": "Catfish", "text_with_ws": "Catfish "},
-#                 {"text": "Keith", "text_with_ws": "Keith "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "2009", "text_with_ws": "2009"},
-#                 {"text": ")", "text_with_ws": ") "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "Fish", "text_with_ws": "Fish "},
-#                 {"text": "Tail", "text_with_ws": "Tail "},
-#                 {"text": "Records)Remember", "text_with_ws": "Records)Remember"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "on", "text_with_ws": "on "},
-#                 {"text": "stage", "text_with_ws": "stage "},
-#                 {"text": "at", "text_with_ws": "at "},
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Half", "text_with_ws": "Half "},
-#                 {"text": "Moon", "text_with_ws": "Moon "},
-#                 {"text": "–", "text_with_ws": "– "},
-#                 {"text": "Latin", "text_with_ws": "Latin "},
-#                 {"text": "Quarter", "text_with_ws": "Quarter "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "2023", "text_with_ws": "2023"},
-#                 {"text": ")", "text_with_ws": ") "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "Westpark", "text_with_ws": "Westpark "},
-#                 {"text": "Music", "text_with_ws": "Music"},
-#                 {"text": ")", "text_with_ws": ")"},
-#             ]
-#         ],
-#         [
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "pub", "text_with_ws": "pub "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "served", "text_with_ws": "served "},
-#                 {"text": "by", "text_with_ws": "by "},
-#                 {"text": "Transport", "text_with_ws": "Transport "},
-#                 {"text": "for", "text_with_ws": "for "},
-#                 {"text": "London", "text_with_ws": "London "},
-#                 {"text": "buses", "text_with_ws": "buses "},
-#                 {"text": "22", "text_with_ws": "22"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "265", "text_with_ws": "265"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "378", "text_with_ws": "378"},
-#                 {"text": ",", "text_with_ws": ", "},
-#                 {"text": "485", "text_with_ws": "485 "},
-#                 {"text": "which", "text_with_ws": "which "},
-#                 {"text": "stop", "text_with_ws": "stop "},
-#                 {"text": "on", "text_with_ws": "on "},
-#                 {"text": "the", "text_with_ws": "the "},
-#                 {"text": "Lower", "text_with_ws": "Lower "},
-#                 {"text": "Richmond", "text_with_ws": "Richmond "},
-#                 {"text": "road", "text_with_ws": "road"},
-#                 {"text": ".", "text_with_ws": ". "},
-#             ],
-#             [
-#                 {"text": "Putney", "text_with_ws": "Putney "},
-#                 {"text": "Bridge", "text_with_ws": "Bridge "},
-#                 {"text": "tube", "text_with_ws": "tube "},
-#                 {"text": "station", "text_with_ws": "station "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "District", "text_with_ws": "District "},
-#                 {"text": "line", "text_with_ws": "line"},
-#                 {"text": ")", "text_with_ws": ") "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "12", "text_with_ws": "12 "},
-#                 {"text": "minute", "text_with_ws": "minute "},
-#                 {"text": "walk", "text_with_ws": "walk "},
-#                 {"text": "over", "text_with_ws": "over "},
-#                 {"text": "Putney", "text_with_ws": "Putney "},
-#                 {"text": "Bridge", "text_with_ws": "Bridge "},
-#                 {"text": "and", "text_with_ws": "and "},
-#                 {"text": "Putney", "text_with_ws": "Putney "},
-#                 {"text": "railway", "text_with_ws": "railway "},
-#                 {"text": "station", "text_with_ws": "station "},
-#                 {"text": "(", "text_with_ws": "("},
-#                 {"text": "Southwestern", "text_with_ws": "Southwestern "},
-#                 {"text": "Railway", "text_with_ws": "Railway"},
-#                 {"text": ")", "text_with_ws": ") "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "12", "text_with_ws": "12 "},
-#                 {"text": "minute", "text_with_ws": "minute "},
-#                 {"text": "walk", "text_with_ws": "walk "},
-#                 {"text": "up", "text_with_ws": "up "},
-#                 {"text": "Putney", "text_with_ws": "Putney "},
-#                 {"text": "High", "text_with_ws": "High "},
-#                 {"text": "Street", "text_with_ws": "Street"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#             [
-#                 {"text": "The", "text_with_ws": "The "},
-#                 {"text": "Santander", "text_with_ws": "Santander "},
-#                 {"text": "Cycles", "text_with_ws": "Cycles "},
-#                 {"text": "Putney", "text_with_ws": "Putney "},
-#                 {"text": "Pier", "text_with_ws": "Pier "},
-#                 {"text": "docking", "text_with_ws": "docking "},
-#                 {"text": "station", "text_with_ws": "station "},
-#                 {"text": "is", "text_with_ws": "is "},
-#                 {"text": "a", "text_with_ws": "a "},
-#                 {"text": "three", "text_with_ws": "three "},
-#                 {"text": "minute", "text_with_ws": "minute "},
-#                 {"text": "walk", "text_with_ws": "walk"},
-#                 {"text": ".", "text_with_ws": "."},
-#             ],
-#         ],
-#         [
-#             [
-#                 {"text": "Official", "text_with_ws": "Official "},
-#                 {"text": "website", "text_with_ws": "website"},
-#             ]
-#         ],
-#     ],
-#     "top_spans": [
-#         [0, 2],
-#         [4, 13],
-#         [11, 13],
-#         [13, 13],
-#         [15, 15],
-#         [17, 26],
-#         [17, 36],
-#         [19, 21],
-#         [19, 26],
-#         [30, 30],
-#         [31, 32],
-#         [33, 34],
-#         [36, 36],
-#         [38, 39],
-#         [42, 49],
-#         [42, 56],
-#         [46, 49],
-#         [52, 56],
-#         [53, 53],
-#         [58, 60],
-#         [62, 74],
-#         [64, 65],
-#         [64, 74],
-#         [77, 79],
-#         [81, 88],
-#         [87, 88],
-#         [90, 90],
-#         [94, 96],
-#         [94, 97],
-#         [94, 100],
-#         [99, 100],
-#         [102, 103],
-#         [105, 105],
-#         [106, 107],
-#         [108, 109],
-#         [111, 111],
-#         [111, 112],
-#         [115, 129],
-#         [115, 131],
-#         [122, 123],
-#         [122, 129],
-#         [122, 131],
-#         [125, 125],
-#         [125, 126],
-#         [128, 129],
-#         [131, 131],
-#         [138, 139],
-#         [143, 143],
-#         [144, 148],
-#         [144, 154],
-#         [150, 154],
-#         [156, 156],
-#         [158, 162],
-#         [158, 169],
-#         [161, 162],
-#         [164, 166],
-#         [164, 169],
-#         [168, 169],
-#         [171, 172],
-#         [174, 175],
-#         [174, 184],
-#         [177, 178],
-#         [180, 181],
-#         [183, 184],
-#         [186, 188],
-#         [186, 189],
-#         [186, 196],
-#         [191, 192],
-#         [195, 196],
-#         [198, 215],
-#         [203, 215],
-#         [204, 205],
-#         [209, 212],
-#         [209, 215],
-#         [214, 214],
-#         [214, 215],
-#         [218, 220],
-#         [221, 221],
-#         [223, 223],
-#         [224, 225],
-#         [224, 228],
-#         [227, 228],
-#         [231, 232],
-#         [238, 252],
-#         [241, 246],
-#         [241, 252],
-#         [248, 250],
-#         [248, 252],
-#         [255, 255],
-#         [255, 263],
-#         [258, 260],
-#         [262, 262],
-#         [262, 263],
-#         [266, 274],
-#         [273, 274],
-#         [276, 278],
-#         [280, 288],
-#         [283, 288],
-#         [292, 292],
-#         [293, 295],
-#         [297, 297],
-#         [310, 312],
-#         [315, 337],
-#         [315, 338],
-#         [320, 320],
-#         [328, 329],
-#         [340, 345],
-#         [343, 345],
-#         [347, 348],
-#         [349, 349],
-#         [350, 356],
-#         [352, 352],
-#         [352, 356],
-#         [354, 355],
-#         [358, 362],
-#         [365, 370],
-#         [366, 367],
-#         [369, 370],
-#         [375, 375],
-#         [377, 378],
-#         [377, 379],
-#         [381, 387],
-#         [389, 389],
-#         [389, 400],
-#         [391, 391],
-#         [398, 400],
-#         [402, 402],
-#         [403, 409],
-#         [407, 409],
-#         [416, 416],
-#         [419, 421],
-#         [419, 425],
-#         [427, 432],
-#         [431, 432],
-#         [434, 435],
-#         [437, 437],
-#         [441, 443],
-#         [445, 445],
-#         [450, 454],
-#         [456, 460],
-#         [462, 464],
-#         [470, 485],
-#         [482, 482],
-#         [484, 485],
-#         [490, 490],
-#         [492, 493],
-#         [495, 496],
-#         [501, 504],
-#         [510, 511],
-#         [513, 514],
-#         [517, 517],
-#         [517, 518],
-#         [518, 518],
-#         [520, 522],
-#         [524, 524],
-#         [527, 528],
-#         [527, 534],
-#         [530, 531],
-#         [537, 537],
-#         [538, 538],
-#         [539, 548],
-#         [543, 548],
-#         [550, 564],
-#         [553, 558],
-#         [553, 564],
-#         [554, 555],
-#         [554, 556],
-#         [560, 561],
-#         [563, 564],
-#         [565, 565],
-#         [566, 567],
-#         [572, 575],
-#         [574, 574],
-#         [574, 575],
-#         [577, 579],
-#         [582, 582],
-#         [585, 585],
-#         [587, 589],
-#         [591, 591],
-#         [593, 602],
-#         [606, 606],
-#         [608, 608],
-#         [610, 611],
-#         [613, 614],
-#         [616, 618],
-#         [620, 621],
-#         [623, 625],
-#         [627, 627],
-#         [629, 629],
-#         [631, 632],
-#         [634, 635],
-#         [634, 651],
-#         [637, 637],
-#         [639, 640],
-#         [642, 644],
-#         [642, 645],
-#         [642, 651],
-#         [647, 648],
-#         [647, 675],
-#         [650, 651],
-#         [653, 655],
-#         [653, 657],
-#         [659, 672],
-#         [674, 675],
-#         [677, 678],
-#         [677, 705],
-#         [680, 685],
-#         [680, 693],
-#         [680, 705],
-#         [687, 688],
-#         [687, 693],
-#         [687, 716],
-#         [690, 691],
-#         [690, 693],
-#         [690, 716],
-#         [693, 693],
-#         [695, 696],
-#         [695, 716],
-#         [698, 699],
-#         [701, 702],
-#         [701, 705],
-#         [704, 705],
-#         [707, 708],
-#         [707, 712],
-#         [710, 712],
-#         [714, 716],
-#         [714, 738],
-#         [718, 719],
-#         [718, 722],
-#         [718, 734],
-#         [718, 738],
-#         [721, 721],
-#         [721, 722],
-#         [724, 725],
-#         [727, 728],
-#         [730, 731],
-#         [733, 734],
-#         [736, 738],
-#         [748, 748],
-#         [752, 754],
-#         [752, 757],
-#         [759, 759],
-#         [766, 767],
-#         [766, 779],
-#         [766, 785],
-#         [769, 770],
-#         [772, 773],
-#         [772, 779],
-#         [772, 785],
-#         [772, 801],
-#         [775, 776],
-#         [775, 779],
-#         [775, 785],
-#         [775, 791],
-#         [775, 801],
-#         [775, 803],
-#         [778, 779],
-#         [778, 801],
-#         [778, 806],
-#         [781, 782],
-#         [781, 785],
-#         [781, 791],
-#         [781, 801],
-#         [781, 806],
-#         [781, 807],
-#         [781, 809],
-#         [781, 810],
-#         [784, 785],
-#         [784, 801],
-#         [784, 807],
-#         [784, 810],
-#         [787, 788],
-#         [787, 789],
-#         [787, 791],
-#         [787, 800],
-#         [787, 801],
-#         [787, 803],
-#         [787, 806],
-#         [787, 809],
-#         [787, 810],
-#         [787, 816],
-#         [790, 791],
-#         [790, 801],
-#         [790, 806],
-#         [790, 807],
-#         [790, 809],
-#         [790, 816],
-#         [793, 794],
-#         [793, 801],
-#         [793, 816],
-#         [796, 797],
-#         [796, 801],
-#         [796, 809],
-#         [796, 810],
-#         [796, 822],
-#         [799, 800],
-#         [802, 802],
-#         [802, 803],
-#         [802, 806],
-#         [802, 816],
-#         [802, 823],
-#         [802, 831],
-#         [805, 806],
-#         [805, 831],
-#         [808, 809],
-#         [808, 831],
-#         [808, 832],
-#         [811, 813],
-#         [811, 816],
-#         [811, 822],
-#         [811, 825],
-#         [811, 831],
-#         [811, 832],
-#         [811, 837],
-#         [811, 838],
-#         [815, 816],
-#         [818, 819],
-#         [821, 822],
-#         [823, 823],
-#         [824, 825],
-#         [824, 828],
-#         [824, 831],
-#         [824, 838],
-#         [824, 852],
-#         [827, 828],
-#         [830, 831],
-#         [833, 834],
-#         [833, 837],
-#         [833, 843],
-#         [833, 849],
-#         [833, 852],
-#         [836, 837],
-#         [839, 840],
-#         [839, 843],
-#         [839, 852],
-#         [842, 843],
-#         [845, 846],
-#         [845, 849],
-#         [848, 849],
-#         [851, 852],
-#         [854, 871],
-#         [854, 881],
-#         [856, 858],
-#         [860, 864],
-#         [860, 870],
-#         [865, 865],
-#         [866, 866],
-#         [869, 870],
-#         [872, 872],
-#         [872, 900],
-#         [875, 875],
-#         [877, 878],
-#         [880, 880],
-#         [880, 881],
-#         [883, 884],
-#         [886, 886],
-#         [888, 890],
-#         [892, 893],
-#         [895, 895],
-#         [897, 913],
-#         [897, 917],
-#         [898, 917],
-#         [902, 917],
-#         [903, 917],
-#         [905, 907],
-#         [905, 910],
-#         [912, 912],
-#         [914, 917],
-#         [915, 916],
-#         [918, 919],
-#         [923, 933],
-#         [923, 940],
-#         [925, 925],
-#         [925, 933],
-#         [925, 940],
-#         [935, 935],
-#         [937, 940],
-#         [942, 943],
-#         [942, 949],
-#         [947, 948],
-#         [951, 954],
-#         [951, 957],
-#         [956, 957],
-#         [959, 959],
-#         [959, 965],
-#         [963, 964],
-#         [967, 970],
-#         [967, 974],
-#         [972, 974],
-#         [976, 982],
-#         [977, 977],
-#         [977, 978],
-#         [977, 980],
-#         [979, 979],
-#         [979, 980],
-#         [984, 987],
-#         [989, 990],
-#     ],
-#     "antecedents": [
-#         None,
-#         None,
-#         None,
-#         None,
-#         [0, 2],
-#         None,
-#         None,
-#         [13, 13],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [0, 2],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [13, 13],
-#         [0, 2],
-#         None,
-#         [13, 13],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [58, 60],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [36, 36],
-#         [115, 131],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [144, 148],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [58, 60],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [276, 278],
-#         [58, 60],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [177, 178],
-#         None,
-#         None,
-#         [347, 348],
-#         None,
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         [183, 184],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [381, 387],
-#         None,
-#         [13, 13],
-#         [310, 312],
-#         None,
-#         None,
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [434, 435],
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [470, 485],
-#         None,
-#         None,
-#         [407, 409],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [58, 60],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [520, 522],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [520, 522],
-#         None,
-#         [310, 312],
-#         None,
-#         [445, 445],
-#         [58, 60],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [510, 511],
-#         None,
-#         [94, 96],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [347, 348],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [195, 196],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [224, 225],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [419, 421],
-#         None,
-#         [610, 611],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [381, 387],
-#         None,
-#         None,
-#         [13, 13],
-#         [869, 870],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         [310, 312],
-#         None,
-#         None,
-#         None,
-#         None,
-#         [38, 39],
-#         None,
-#         None,
-#         [875, 875],
-#         None,
-#         None,
-#         None,
-#         [46, 49],
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#         None,
-#     ],
-# }