def to_model(self): # Create a citation object as in our models. Eventually, the version in # our models should probably be the only object named "Citation". Until # then, this function helps map from this object to the Citation object # in the models. c = ModelCitation( **{ key: value for key, value in self.__dict__.items() if key in ModelCitation._meta.get_all_field_names() }) canon = REPORTERS[self.canonical_reporter] cite_type = canon[self.lookup_index]["cite_type"] c.type = map_reporter_db_cite_type(cite_type) return c
def merge_or_add_opinions( cluster_id: int, html_str: str, data: Dict[str, Any], date_argued: datetime.date, date_filed: datetime.date, case_names: Dict[str, str], status: str, docket_number: str, found_citations: List[FoundCitation], ) -> Optional[Docket]: """Merge opinions if applicable. If opinion not in system, merge or add to cluster. If opinion in system came from harvard, add new opinion to cluster, else we merge new opinion data into scraped opinion. :param cluster_id: Opinion Cluster id. :param html_str: HTML opinion to add. :param data: Case data to import. :param date_argued: Date case was argued. :param date_filed: Date case was filed. :param case_names: A dict with the three case name types :param status: Whether it's precedential :param docket_number: The docket number :param found_citations: A list of FoundCitation objects. :return: The merged docket, cluster, and opinion. """ does_exist = (Opinion.objects.filter(cluster_id=cluster_id).exclude( html_anon_2020="").exists()) if does_exist: logger.info(f"Opinion already in database at {cluster_id}") return logger.info(f"Starting merger of opinions in cluster {cluster_id}.") cluster = OpinionCluster.objects.get(pk=cluster_id) docket = cluster.docket # Dates are uniformly good in our dataset # validation and is_approx not needed # Merge docket information docket.add_anon_2020_source() docket.date_argued = date_argued or docket.date_argued docket.docket_number = docket_number or docket.docket_number docket.case_name_short = (case_names["case_name_short"] or docket.case_name_short) docket.case_name = case_names["case_name"] or docket.case_name docket.case_name_full = (case_names["case_name_full"] or docket.case_name_full) # Merge cluster information cluster.date_filed = date_filed or cluster.date_filed cluster.precedential_status = status or cluster.precedential_status cluster.attorneys = data["representation"] or cluster.attorneys cluster.disposition = data["summary_disposition"] or cluster.disposition cluster.summary = data["summary_court"] or cluster.summary cluster.history = data["history"] or cluster.history cluster.cross_reference = (data["history_docket_numbers"] or cluster.cross_reference) cluster.correction = data["publication_status_note"] or cluster.correction if data["judges"]: cluster.judges = (data["judges"].replace("{", "").replace("}", "") or cluster.judges) cluster.case_name_short = (case_names["case_name_short"] or cluster.case_name_short) cluster.case_name = case_names["case_name"] or cluster.case_name cluster.case_name_full = (case_names["case_name_full"] or cluster.case_name_full) docket.save() cluster.save() # Add citations to cluster if applicable for citation in found_citations: Citation.objects.get_or_create( volume=citation.volume, reporter=citation.reporter, page=citation.page, type=map_reporter_db_cite_type( REPORTERS[citation.canonical_reporter][0]["cite_type"]), cluster_id=cluster.id, ) # Merge with scrape or add opinion to cluster with harvard if OpinionCluster.objects.get(pk=cluster_id).source == "C": opinion = Opinion.objects.get(cluster_id=cluster_id) logger.info("Merge with Harvard data") opinion.html_anon_2020 = html_str else: opinion = Opinion( cluster_id=cluster.id, type=Opinion.COMBINED, html_anon_2020=html_str, extracted_by_ocr=False, ) opinion.save() logger.info(f"Finished merging opinion in cluster {cluster_id}.") return docket
def parse_harvard_opinions(reporter, volume, make_searchable): """ Parse downloaded CaseLaw Corpus from internet archive and add them to our database. Optionally uses a reporter abbreviation to identify cases to download as used by IA. (Ex. T.C. => tc) Optionally uses a volume integer. If neither is provided, code will cycle through all downloaded files. :param volume: The volume (int) of the reporters (optional) (ex 10) :param reporter: Reporter string as slugify'd (optional) (tc) for T.C. :param make_searchable: Boolean to indicate saving to solr :return: None """ if not reporter and volume: logger.error("You provided a volume but no reporter. Exiting.") return for file_path in filepath_list(reporter, volume): ia_download_url = "/".join( ["https://archive.org/download", file_path.split("/", 9)[-1]] ) if OpinionCluster.objects.filter( filepath_json_harvard=file_path ).exists(): logger.info("Skipping - already in system %s" % ia_download_url) continue try: with open(file_path) as f: data = json.load(f) except ValueError: logger.warning("Empty json: missing case at: %s" % ia_download_url) continue except Exception as e: logger.warning("Unknown error %s for: %s" % (e, ia_download_url)) continue cites = get_citations(data["citations"][0]["cite"]) if not cites: logger.info( "No citation found for %s." % data["citations"][0]["cite"] ) continue case_name = harmonize(data["name_abbreviation"]) case_name_short = cnt.make_case_name_short(case_name) case_name_full = harmonize(data["name"]) citation = cites[0] if skip_processing(citation, case_name, file_path): continue # TODO: Generalize this to handle all court types somehow. court_id = match_court_string( data["court"]["name"], state=True, federal_appeals=True, federal_district=True, ) soup = BeautifulSoup(data["casebody"]["data"], "lxml") # Some documents contain images in the HTML # Flag them for a later crawl by using the placeholder '[[Image]]' judge_list = [ extract_judge_last_name(x.text) for x in soup.find_all("judges") ] author_list = [ extract_judge_last_name(x.text) for x in soup.find_all("author") ] # Flatten and dedupe list of judges judges = ", ".join( sorted( list( set( itertools.chain.from_iterable(judge_list + author_list) ) ) ) ) judges = titlecase(judges) docket_string = ( data["docket_number"] .replace("Docket No.", "") .replace("Docket Nos.", "") .strip() ) short_fields = ["attorneys", "disposition", "otherdate", "seealso"] long_fields = [ "syllabus", "summary", "history", "headnotes", "correction", ] short_data = parse_extra_fields(soup, short_fields, False) long_data = parse_extra_fields(soup, long_fields, True) with transaction.atomic(): logger.info("Adding docket for: %s", citation.base_citation()) docket = Docket( case_name=case_name, case_name_short=case_name_short, case_name_full=case_name_full, docket_number=docket_string, court_id=court_id, source=Docket.HARVARD, ia_needs_upload=False, ) try: with transaction.atomic(): docket.save() except OperationalError as e: if "exceeds maximum" in str(e): docket.docket_number = ( "%s, See Corrections for full Docket Number" % trunc(docket_string, length=5000, ellipsis="...") ) docket.save() long_data["correction"] = "%s <br> %s" % ( data["docket_number"], long_data["correction"], ) # Handle partial dates by adding -01v to YYYY-MM dates date_filed, is_approximate = validate_dt(data["decision_date"]) logger.info("Adding cluster for: %s", citation.base_citation()) cluster = OpinionCluster( case_name=case_name, case_name_short=case_name_short, case_name_full=case_name_full, precedential_status="Published", docket_id=docket.id, source="U", date_filed=date_filed, date_filed_is_approximate=is_approximate, attorneys=short_data["attorneys"], disposition=short_data["disposition"], syllabus=long_data["syllabus"], summary=long_data["summary"], history=long_data["history"], other_dates=short_data["otherdate"], cross_reference=short_data["seealso"], headnotes=long_data["headnotes"], correction=long_data["correction"], judges=judges, filepath_json_harvard=file_path, ) cluster.save(index=False) logger.info("Adding citation for: %s", citation.base_citation()) Citation.objects.create( volume=citation.volume, reporter=citation.reporter, page=citation.page, type=map_reporter_db_cite_type( REPORTERS[citation.canonical_reporter][0]["cite_type"] ), cluster_id=cluster.id, ) new_op_pks = [] for op in soup.find_all("opinion"): # This code cleans author tags for processing. # It is particularly useful for identifiying Per Curiam for elem in [op.find("author")]: if elem is not None: [x.extract() for x in elem.find_all("page-number")] auth = op.find("author") if auth is not None: author_tag_str = titlecase(auth.text.strip(":")) author_str = titlecase( "".join(extract_judge_last_name(author_tag_str)) ) else: author_str = "" author_tag_str = "" per_curiam = True if author_tag_str == "Per Curiam" else False # If Per Curiam is True set author string to Per Curiam if per_curiam: author_str = "Per Curiam" op_type = map_opinion_type(op.get("type")) opinion_xml = str(op) logger.info("Adding opinion for: %s", citation.base_citation()) op = Opinion( cluster_id=cluster.id, type=op_type, author_str=author_str, xml_harvard=opinion_xml, per_curiam=per_curiam, extracted_by_ocr=True, ) # Don't index now; do so later if desired op.save(index=False) new_op_pks.append(op.pk) if make_searchable: add_items_to_solr.delay(new_op_pks, "search.Opinion") logger.info("Finished: %s", citation.base_citation())
def add_new_records( html_str: str, data: Dict[str, Any], date_argued: datetime.date, date_filed: datetime.date, case_names: Dict[str, str], status: str, docket_number: str, found_citations: List[FoundCitation], court_id: str, ) -> Docket: """Create new records in the DB based on parsed data :param html_str: HTML opinion to add :param data: Case data to import :param date_argued: Date case was argued. :param date_filed: Date case was filed. :param case_names: A dict with the three case name types :param status: Whether it's precedential :param docket_number: The docket number :param found_citations: A list of FoundCitation objects. :param court_id: The CL id of the court :return: None. """ docket = Docket.objects.create( **case_names, docket_number=docket_number, court_id=court_id, source=Docket.ANON_2020, ia_needs_upload=False, date_argued=date_argued, ) logger.info("Add cluster for: %s", found_citations[0].base_citation()) judges = data["judges"] or "" cluster = OpinionCluster( **case_names, precedential_status=status, docket_id=docket.id, source=docket.ANON_2020, date_filed=date_filed, attorneys=data["representation"] or "", disposition=data["summary_disposition"] or "", summary=data["summary_court"] or "", history=data["history"] or "", cross_reference=data["history_docket_numbers"] or "", correction=data["publication_status_note"] or "", judges=judges.replace("{", "").replace("}", "") or "", ) cluster.save(index=False) for citation in found_citations: logger.info("Adding citation for: %s", citation.base_citation()) Citation.objects.get_or_create( volume=citation.volume, reporter=citation.reporter, page=citation.page, type=map_reporter_db_cite_type( REPORTERS[citation.canonical_reporter][0]["cite_type"]), cluster_id=cluster.id, ) op = Opinion( cluster_id=cluster.id, type=Opinion.COMBINED, html_anon_2020=html_str, extracted_by_ocr=False, ) op.save() logger.info( f"Finished importing cluster {cluster.id}; {found_citations[0].base_citation()}" ) return docket
def parse_harvard_opinions(reporter, volume): """ Parse downloaded CaseLaw Corpus from internet archive and add them to our database. Optionally uses a reporter abbreviation to identify cases to download as used by IA. (Ex. T.C. => tc) Optionally uses a volume integer. If neither is provided, code will cycle through all downloaded files. :param volume: The volume (int) of the reporters (optional) (ex 10) :param reporter: Reporter string as slugify'd (optional) (tc) for T.C. :return: None """ if not reporter and volume: logger.error("You provided a volume but no reporter. Exiting.") return for file_path in filepath_list(reporter, volume): ia_download_url = "/".join( ["https://archive.org/download", file_path.split("/", 9)[-1]] ) if OpinionCluster.objects.filter( filepath_json_harvard=file_path ).exists(): logger.info("Skipping - already in system %s" % ia_download_url) continue try: with open(file_path) as f: data = json.load(f) except ValueError: logger.warning("Empty json: missing case at: %s" % ia_download_url) continue except Exception as e: logger.warning("Unknown error %s for: %s" % (e, ia_download_url)) continue cites = get_citations(data["citations"][0]["cite"], html=False) if not cites: logger.info( "No citation found for %s." % data["citations"][0]["cite"] ) continue case_name = harmonize(data["name_abbreviation"]) case_name_short = cnt.make_case_name_short(case_name) case_name_full = harmonize(data["name"]) citation = cites[0] if skip_processing(citation, case_name): continue # TODO: Generalize this to handle all court types somehow. court_id = match_court_string( data["court"]["name"], state=True, federal_appeals=True, federal_district=True, ) soup = BeautifulSoup(data["casebody"]["data"], "lxml") # Some documents contain images in the HTML # Flag them for a later crawl by using the placeholder '[[Image]]' judge_list = [ find_judge_names(x.text) for x in soup.find_all("judges") ] author_list = [ find_judge_names(x.text) for x in soup.find_all("author") ] # Flatten and dedupe list of judges judges = ", ".join( list(set(itertools.chain.from_iterable(judge_list + author_list))) ) judges = titlecase(judges) docket_string = ( data["docket_number"] .replace("Docket No.", "") .replace("Docket Nos.", "") .strip() ) with transaction.atomic(): logger.info("Adding docket for: %s", citation.base_citation()) docket = Docket.objects.create( case_name=case_name, case_name_short=case_name_short, case_name_full=case_name_full, docket_number=docket_string, court_id=court_id, source=Docket.HARVARD, ia_needs_upload=False, ) # Iterate over other xml fields in Harvard data set # and save as string list for further processing at a later date. json_fields = [ "attorneys", "disposition", "syllabus", "summary", "history", "otherdate", "seealso", "headnotes", "correction", ] data_set = {} while json_fields: key = json_fields.pop(0) data_set[key] = "|".join([x.text for x in soup.find_all(key)]) # Handle partial dates by adding -01v to YYYY-MM dates date_filed, is_approximate = validate_dt(data["decision_date"]) logger.info("Adding cluster for: %s", citation.base_citation()) cluster = OpinionCluster.objects.create( case_name=case_name, case_name_short=case_name_short, case_name_full=case_name_full, precedential_status="Published", docket_id=docket.id, source="U", date_filed=date_filed, date_filed_is_approximate=is_approximate, attorneys=data_set["attorneys"], disposition=data_set["disposition"], syllabus=data_set["syllabus"], summary=data_set["summary"], history=data_set["history"], other_dates=data_set["otherdate"], cross_reference=data_set["seealso"], headnotes=data_set["headnotes"], correction=data_set["correction"], judges=judges, filepath_json_harvard=file_path, ) logger.info("Adding citation for: %s", citation.base_citation()) Citation.objects.create( volume=citation.volume, reporter=citation.reporter, page=citation.page, type=map_reporter_db_cite_type( REPORTERS[citation.reporter][0]["cite_type"] ), cluster_id=cluster.id, ) for op in soup.find_all("opinion"): joined_by_str = titlecase( " ".join( list(set(itertools.chain.from_iterable(judge_list))) ) ) author_str = titlecase( " ".join( list(set(itertools.chain.from_iterable(author_list))) ) ) op_type = map_opinion_type(op.get("type")) opinion_xml = str(op) logger.info("Adding opinion for: %s", citation.base_citation()) Opinion.objects.create( cluster_id=cluster.id, type=op_type, author_str=author_str, xml_harvard=opinion_xml, joined_by_str=joined_by_str, extracted_by_ocr=True, ) logger.info("Finished: %s", citation.base_citation())