Пример #1
0
    def get_subject(self, key, details=False, offset=0, limit=12, sort='first_publish_year desc', **filters):
        meta = self.get_meta(key)

        q = self.make_query(key, filters)
        subject_type = meta.name
        name = meta.path.replace("_", " ")

        if details:
            kw = self.query_optons_for_details()
        else:
            kw = {}

        from search import work_search
        result = work_search(q, offset=offset, limit=limit, sort=sort, **kw)
        for w in result.docs:
            w.ia = w.ia and w.ia[0] or None
            if not w.get('public_scan') and w.ia and w.get('lending_edition'):
                doc = web.ctx.site.store.get("ebooks/books/" + w['lending_edition']) or {}
                w['checked_out'] = doc.get("borrowed") == "true"

            # XXX-Anand: Oct 2013
            # Somewhere something is broken, work keys are coming as OL1234W/works/
            # Quick fix it solve that issue.
            if w.key.endswith("/works/"):
                w.key = "/works/" + w.key.replace("/works/", "")
                
        subject = Subject(
            key=key,
            name=name,
            subject_type=subject_type,
            work_count = result['num_found'],
            works=result['docs']
        )

        if details:
            subject.ebook_count = dict(result.facets["has_fulltext"]).get("true", 0)
            #subject.ebook_count = self.get_ebook_count(meta.name, q[meta.facet_key], q.get('publish_year'))

            subject.subjects = result.facets["subject_facet"]
            subject.places = result.facets["place_facet"]
            subject.people = result.facets["person_facet"]
            subject.times = result.facets["time_facet"]

            subject.authors = result.facets["author_facet"]
            subject.publishers = result.facets["publisher_facet"]
            subject.languages = result.facets['language']

            # Ignore bad dates when computing publishing_history
            # year < 1000 or year > current_year+1 are considered bad dates
            current_year = datetime.datetime.utcnow().year
            subject.publishing_history = [[year, count] for year, count in result.facets["publish_year"] if 1000 < year <= current_year+1]

            # strip self from subjects and use that to find exact name
            for i, s in enumerate(subject[meta.key]):
                if "key" in s and s.key.lower() == key.lower():
                    subject.name = s.name;
                    subject[meta.key].pop(i)
                    break

        return subject
Пример #2
0
    def get_subject(self, key, details=False, offset=0, limit=12, sort="first_publish_year desc", **filters):
        meta = self.get_meta(key)

        q = self.make_query(key, filters)
        subject_type = meta.name
        name = meta.path.replace("_", " ")

        if details:
            kw = self.query_optons_for_details()
        else:
            kw = {}

        from search import work_search

        result = work_search(q, offset=offset, limit=limit, sort=sort, **kw)
        for w in result.docs:
            w.ia = w.ia and w.ia[0] or None
            if not w.get("public_scan") and w.ia and w.get("lending_edition"):
                doc = web.ctx.site.store.get("ebooks/books/" + w["lending_edition"]) or {}
                w["checked_out"] = doc.get("borrowed") == "true"

            # XXX-Anand: Oct 2013
            # Somewhere something is broken, work keys are coming as OL1234W/works/
            # Quick fix it solve that issue.
            if w.key.endswith("/works/"):
                w.key = "/works/" + w.key.replace("/works/", "")

        subject = Subject(
            key=key, name=name, subject_type=subject_type, work_count=result["num_found"], works=result["docs"]
        )

        if details:
            subject.ebook_count = dict(result.facets["has_fulltext"]).get("true", 0)
            # subject.ebook_count = self.get_ebook_count(meta.name, q[meta.facet_key], q.get('publish_year'))

            subject.subjects = result.facets["subject_facet"]
            subject.places = result.facets["place_facet"]
            subject.people = result.facets["person_facet"]
            subject.times = result.facets["time_facet"]

            subject.authors = result.facets["author_facet"]
            subject.publishers = result.facets["publisher_facet"]
            subject.languages = result.facets["language"]

            # Ignore bad dates when computing publishing_history
            # year < 1000 or year > current_year+1 are considered bad dates
            current_year = datetime.datetime.utcnow().year
            subject.publishing_history = [
                [year, count] for year, count in result.facets["publish_year"] if 1000 < year <= current_year + 1
            ]

            # strip self from subjects and use that to find exact name
            for i, s in enumerate(subject[meta.key]):
                if "key" in s and s.key.lower() == key.lower():
                    subject.name = s.name
                    subject[meta.key].pop(i)
                    break

        return subject
Пример #3
0
    def get_subject(self,
                    key,
                    details=False,
                    offset=0,
                    limit=12,
                    sort='first_publish_year desc',
                    **filters):
        meta = self.get_meta(key)

        q = self.make_query(key, filters)
        subject_type = meta.name
        name = meta.path.replace("_", " ")

        if details:
            kw = self.query_optons_for_details()
        else:
            kw = {}

        from search import work_search
        result = work_search(q, offset=offset, limit=limit, sort=sort, **kw)
        for w in result.docs:
            w.ia = w.ia and w.ia[0] or None

        subject = Subject(key=key,
                          name=name,
                          subject_type=subject_type,
                          work_count=result['num_found'],
                          works=result['docs'])

        if details:
            #subject.ebook_count = dict(result.facets["has_fulltext"]).get("true", 0)
            subject.ebook_count = self.get_ebook_count(meta.name,
                                                       q[meta.facet_key],
                                                       q.get('publish_year'))

            subject.subjects = result.facets["subject_facet"]
            subject.places = result.facets["place_facet"]
            subject.people = result.facets["person_facet"]
            subject.times = result.facets["time_facet"]

            subject.authors = result.facets["author_facet"]
            subject.publishers = result.facets["publisher_facet"]

            subject.publishing_history = [[
                year, count
            ] for year, count in result.facets["publish_year"] if year > 1000]

            # strip self from subjects and use that to find exact name
            for i, s in enumerate(subject[meta.key]):
                if s.key.lower() == key.lower():
                    subject.name = s.name
                    subject[meta.key].pop(i)
                    break

        return subject
Пример #4
0
    def get_subject(self, key, details=False, offset=0, limit=12, sort='first_publish_year desc', **filters):
        meta = self.get_meta(key)

        q = self.make_query(key, filters)
        subject_type = meta.name
        name = meta.path.replace("_", " ")

        if details:
            kw = self.query_optons_for_details()
        else:
            kw = {}

        from search import work_search
        result = work_search(q, offset=offset, limit=limit, sort=sort, **kw)
        for w in result.docs:
            w.ia = w.ia and w.ia[0] or None
            if not w.get('public_scan') and w.ia and w.get('lending_edition'):
                doc = web.ctx.site.store.get("ebooks/books/" + w['lending_edition']) or {}
                w['checked_out'] = doc.get("borrowed") == "true"
                
        subject = Subject(
            key=key,
            name=name,
            subject_type=subject_type,
            work_count = result['num_found'],
            works=result['docs']
        )

        if details:
            subject.ebook_count = dict(result.facets["has_fulltext"]).get("true", 0)
            #subject.ebook_count = self.get_ebook_count(meta.name, q[meta.facet_key], q.get('publish_year'))

            subject.subjects = result.facets["subject_facet"]
            subject.places = result.facets["place_facet"]
            subject.people = result.facets["person_facet"]
            subject.times = result.facets["time_facet"]

            subject.authors = result.facets["author_facet"]
            subject.publishers = result.facets["publisher_facet"]
            subject.languages = result.facets['language']

            subject.publishing_history = [[year, count] for year, count in result.facets["publish_year"] if year > 1000]

            # strip self from subjects and use that to find exact name
            for i, s in enumerate(subject[meta.key]):
                if "key" in s and s.key.lower() == key.lower():
                    subject.name = s.name;
                    subject[meta.key].pop(i)
                    break

        return subject
Пример #5
0
def get_subject(key, details=False, offset=0, limit=12, **filters):
    """Returns data related to a subject.

    By default, it returns a storage object with key, name, work_count and works. 
    The offset and limit arguments are used to get the works.
        
        >>> get_subject("/subjects/Love") #doctest: +SKIP
        {
            "key": "/subjects/Love", 
            "name": "Love",
            "work_count": 5129, 
            "works": [...]
        }
        
    When details=True, facets and ebook_count are additionally added to the result.

    >>> get_subject("/subjects/Love", details=True) #doctest: +SKIP
    {
        "key": "/subjects/Love", 
        "name": "Love",
        "work_count": 5129, 
        "works": [...],
        "ebook_count": 94, 
        "authors": [
            {
                "count": 11, 
                "name": "Plato.", 
                "key": "/authors/OL12823A"
            }, 
            ...
        ],
        "subjects": [
            {
                "count": 1168,
                "name": "Religious aspects", 
                "key": "/subjects/religious aspects"
            }, 
            ...
        ],
        "times": [...],
        "places": [...],
        "people": [...],
        "publishing_history": [[1492, 1], [1516, 1], ...],
        "publishers": [
            {
                "count": 57, 
                "name": "Sine nomine"        
            },
            ...
        ]
    }
    
    Optional arguments limit and offset can be passed to limit the number of works returned and starting offset.
    
    Optional arguments has_fulltext and published_in can be passed to filter the results.
    """
    m = web.re_compile(r'/subjects/(place:|time:|person:|)(.+)').match(key)
    if m:
        prefix = "/subjects/" + m.group(1)
        path = m.group(2)
    else:
        return None
        
    meta = finddict(SUBJECTS, prefix=prefix)
    
    q = {meta.facet_key: str_to_key(path).lower()}
    subject_type = meta.name

    name = path.replace("_", " ")

    def facet_wrapper(facet, value, count):
        if facet == "publish_year":
            return [int(value), count]
        elif facet == "publisher_facet":
            return web.storage(name=value, count=count)
        elif facet == "author_facet":
            author = read_author_facet(value) # FIXME
            return web.storage(name=author[1], key="/authors/" + author[0], count=count)
        elif facet in ["subject_facet", "person_facet", "place_facet", "time_facet"]:
            return web.storage(key=finddict(SUBJECTS, facet=facet).prefix + str_to_key(value).replace(" ", "_"), name=value, count=count)
        elif facet == "has_fulltext":
            return [value, count]
        else:
            return web.storage(name=value, count=count)

    # search for works
    from search import work_search
    kw = {} 
    if details:
        kw['facets'] = [
            {"name": "author_facet", "sort": "count"},
            "language", 
            "publisher_facet", 
            {"name": "publish_year", "limit": -1}, 
            "subject_facet", "person_facet", "place_facet", "time_facet", 
            "has_fulltext"]        
        kw['facet.mincount'] = 1
        kw['facet.limit'] = 25
        kw['facet_wrapper'] = facet_wrapper

    if filters:
        if filters.get("has_fulltext") == "true":
            q['has_fulltext'] = "true"
        if filters.get("publish_year"):
            q['publish_year'] = filters['publish_year']

    result = work_search(q, offset=offset, limit=limit, sort="edition_count desc", **kw)
    for w in result.docs:
        w.ia = w.ia and w.ia[0] or None

    subject = web.storage(
        key=key,
        name=name,
        subject_type=subject_type,
        work_count = result['num_found'],
        works=result['docs']
    )

    if details:
        subject.ebook_count = dict(result.facets["has_fulltext"]).get("true", 0)

        subject.subjects = result.facets["subject_facet"]
        subject.places = result.facets["place_facet"]
        subject.people = result.facets["person_facet"]
        subject.times = result.facets["time_facet"]

        subject.authors = result.facets["author_facet"]        
        subject.publishers = result.facets["publisher_facet"]
        
        subject.publishing_history = [[year, count] for year, count in result.facets["publish_year"] if year > 1000]
        
        # strip self from subjects and use that to find exact name
        for i, s in enumerate(subject[meta.key]):
            if s.key.lower() == key.lower():
                subject.name = s.name;
                subject[meta.key].pop(i)
                break

    return subject