def analyseParagraphsInRevision(revision_curr, revision_prev, text_curr):
# Containers for unmatched and matched paragraphs.
unmatched_paragraphs_curr = []
unmatched_paragraphs_prev = []
matched_paragraphs_prev = []
# Split the text of the current into paragraphs.
paragraphs = Text.splitIntoParagraphs(text_curr)
# Iterate over the paragraphs of the current version.
for paragraph in paragraphs:
# Build Paragraph structure and calculate hash value.
paragraph = paragraph.strip()
hash_curr = Text.calculateHash(paragraph)
matched_curr = False
# If the paragraph is in the previous revision,
# update the authorship information and mark both paragraphs as matched (also in HT).
if (hash_curr in revision_prev.ordered_paragraphs):
for paragraph_prev in revision_prev.paragraphs[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update({paragraph_prev.hash_value : [paragraph_prev]})
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
break
# If the paragraph is not in the previous revision, but it is in an older revision
# update the authorship information and mark both paragraphs as matched.
if ((not matched_curr) and (hash_curr in paragraphs_ht)):
for paragraph_prev in paragraphs_ht[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update({paragraph_prev.hash_value : [paragraph_prev]})
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
break
# If the paragraph did not match with previous revisions,
# add to container of unmatched paragraphs for further analysis.
if (not matched_curr):
paragraph_curr = Paragraph()
paragraph_curr.hash_value = Text.calculateHash(paragraph)
paragraph_curr.value = paragraph
revision_curr.ordered_paragraphs.append(paragraph_curr.hash_value)
if (paragraph_curr.hash_value in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_curr.hash_value].append(paragraph_curr)
else:
revision_curr.paragraphs.update({paragraph_curr.hash_value : [paragraph_curr]})
unmatched_paragraphs_curr.append(paragraph_curr)
# Identify unmatched paragraphs in previous revision for further analysis.
for paragraph_prev_hash in revision_prev.ordered_paragraphs:
for paragraph_prev in revision_prev.paragraphs[paragraph_prev_hash]:
if (not paragraph_prev.matched):
unmatched_paragraphs_prev.append(paragraph_prev)
return (unmatched_paragraphs_curr, unmatched_paragraphs_prev, matched_paragraphs_prev)
def analyseParagraphsInRevision(revision_curr, revision_prev, text_curr, relation):
# Containers for unmatched and matched paragraphs.
unmatched_paragraphs_curr = []
unmatched_paragraphs_prev = []
matched_paragraphs_prev = []
# Split the text of the current into paragraphs.
paragraphs = Text.splitIntoParagraphs(text_curr)
# Iterate over the paragraphs of the current version.
for paragraph in paragraphs:
# Build Paragraph structure and calculate hash value.
paragraph = paragraph.strip()
hash_curr = Text.calculateHash(paragraph)
matched_curr = False
# If the paragraph is in the previous revision,
# update the authorship information and mark both paragraphs as matched (also in HT).
if (hash_curr in revision_prev.ordered_paragraphs):
for paragraph_prev in revision_prev.paragraphs[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
word_prev.used.append(revision_curr.wikipedia_id)
#if (word_prev.revision in relation.reintroduced.keys()):
# relation.reintroduced.update({word_prev.revision : relation.reintroduced[word_prev.revision] + 1 })
#else:
# relation.reintroduced.update({word_prev.revision : 1 })
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update({paragraph_prev.hash_value : [paragraph_prev]})
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
break
# If the paragraph is not in the previous revision, but it is in an older revision
# update the authorship information and mark both paragraphs as matched.
if ((not matched_curr) and (hash_curr in paragraphs_ht)):
for paragraph_prev in paragraphs_ht[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
word_prev.used.append(revision_curr.wikipedia_id)
if (revision_prev.wikipedia_id not in word_prev.used):
word_prev.freq.append(revision_curr.wikipedia_id)
# Revert: reintroducing something that somebody else deleted,
# (and was not used in the previous revision)
if (revision_prev.wikipedia_id not in word_prev.used):
#if (revision_curr.wikipedia_id == 11):
# print "Revert in 11", word_prev.value, word_prev.deleted, relation.revert
for elem in word_prev.deleted:
if (elem in revisions.keys()):
if (revisions[elem].contributor_name != revision_curr.contributor_name):
if (elem in relation.revert.keys()):
relation.revert.update({elem : relation.revert[elem] + 1})
else:
relation.revert.update({elem : 1})
else:
if (elem in relation.self_revert.keys()):
relation.self_revert.update({elem : relation.self_revert[elem] + 1})
else:
relation.self_revert.update({elem : 1})
if (revision_prev.wikipedia_id not in word_prev.used):
if (elem in revisions.keys()):
if (revisions[word_prev.revision].contributor_name != revision_curr.contributor_name):
if (word_prev.revision in relation.reintroduced.keys()):
relation.reintroduced.update({word_prev.revision : relation.reintroduced[word_prev.revision] + 1 })
else:
relation.reintroduced.update({word_prev.revision : 1 })
else:
if (word_prev.revision in relation.self_reintroduced.keys()):
relation.self_reintroduced.update({word_prev.revision : relation.self_reintroduced[word_prev.revision] + 1})
else:
relation.self_reintroduced.update({word_prev.revision : 1})
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update({paragraph_prev.hash_value : [paragraph_prev]})
revision_curr.ordered_paragraphs.append(paragraph_prev.hash_value)
break
# If the paragraph did not match with previous revisions,
# add to container of unmatched paragraphs for further analysis.
if (not matched_curr):
paragraph_curr = Paragraph()
paragraph_curr.hash_value = Text.calculateHash(paragraph)
paragraph_curr.value = paragraph
revision_curr.ordered_paragraphs.append(paragraph_curr.hash_value)
if (paragraph_curr.hash_value in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_curr.hash_value].append(paragraph_curr)
else:
revision_curr.paragraphs.update({paragraph_curr.hash_value : [paragraph_curr]})
unmatched_paragraphs_curr.append(paragraph_curr)
# Identify unmatched paragraphs in previous revision for further analysis.
for paragraph_prev_hash in revision_prev.ordered_paragraphs:
for paragraph_prev in revision_prev.paragraphs[paragraph_prev_hash]:
if (not paragraph_prev.matched):
unmatched_paragraphs_prev.append(paragraph_prev)
return (unmatched_paragraphs_curr, unmatched_paragraphs_prev, matched_paragraphs_prev)
def analyseParagraphsInRevision(revision_curr, revision_prev, text_curr,
relation):
# Containers for unmatched and matched paragraphs.
unmatched_paragraphs_curr = []
unmatched_paragraphs_prev = []
matched_paragraphs_prev = []
# Split the text of the current into paragraphs.
paragraphs = Text.splitIntoParagraphs(text_curr)
# Iterate over the paragraphs of the current version.
for paragraph in paragraphs:
# Build Paragraph structure and calculate hash value.
paragraph = paragraph.strip()
hash_curr = Text.calculateHash(paragraph)
matched_curr = False
# If the paragraph is in the previous revision,
# update the authorship information and mark both paragraphs as matched (also in HT).
if (hash_curr in revision_prev.ordered_paragraphs):
for paragraph_prev in revision_prev.paragraphs[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[
hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
word_prev.used.append(
revision_curr.wikipedia_id)
#if (word_prev.revision in relation.reintroduced.keys()):
# relation.reintroduced.update({word_prev.revision : relation.reintroduced[word_prev.revision] + 1 })
#else:
# relation.reintroduced.update({word_prev.revision : 1 })
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[
paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update(
{paragraph_prev.hash_value: [paragraph_prev]})
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
break
# If the paragraph is not in the previous revision, but it is in an older revision
# update the authorship information and mark both paragraphs as matched.
if ((not matched_curr) and (hash_curr in paragraphs_ht)):
for paragraph_prev in paragraphs_ht[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[
hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
word_prev.used.append(
revision_curr.wikipedia_id)
if (revision_prev.wikipedia_id
not in word_prev.used):
word_prev.freq.append(
revision_curr.wikipedia_id)
# Revert: reintroducing something that somebody else deleted,
# (and was not used in the previous revision)
if (revision_prev.wikipedia_id
not in word_prev.used):
#if (revision_curr.wikipedia_id == 11):
# print "Revert in 11", word_prev.value, word_prev.deleted, relation.revert
for elem in word_prev.deleted:
if (elem in revisions.keys()):
if (revisions[elem].
contributor_name !=
revision_curr.
contributor_name):
if (elem in relation.revert.
keys()):
relation.revert.update({
elem:
relation.revert[elem] +
1
})
else:
relation.revert.update(
{elem: 1})
else:
if (elem in relation.
self_revert.keys()):
relation.self_revert.update(
{
elem:
relation.
self_revert[elem] +
1
})
else:
relation.self_revert.update(
{elem: 1})
if (revision_prev.wikipedia_id
not in word_prev.used):
if (elem in revisions.keys()):
if (revisions[word_prev.revision].
contributor_name !=
revision_curr.contributor_name
):
if (word_prev.revision in relation.
reintroduced.keys()):
relation.reintroduced.update({
word_prev.revision:
relation.reintroduced[
word_prev.revision] + 1
})
else:
relation.reintroduced.update(
{word_prev.revision: 1})
else:
if (word_prev.revision in relation.
self_reintroduced.keys()):
relation.self_reintroduced.update(
{
word_prev.revision:
relation.
self_reintroduced[
word_prev.revision]
+ 1
})
else:
relation.self_reintroduced.update(
{word_prev.revision: 1})
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[
paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update(
{paragraph_prev.hash_value: [paragraph_prev]})
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
break
# If the paragraph did not match with previous revisions,
# add to container of unmatched paragraphs for further analysis.
if (not matched_curr):
paragraph_curr = Paragraph()
paragraph_curr.hash_value = Text.calculateHash(paragraph)
paragraph_curr.value = paragraph
revision_curr.ordered_paragraphs.append(paragraph_curr.hash_value)
if (paragraph_curr.hash_value in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_curr.hash_value].append(
paragraph_curr)
else:
revision_curr.paragraphs.update(
{paragraph_curr.hash_value: [paragraph_curr]})
unmatched_paragraphs_curr.append(paragraph_curr)
# Identify unmatched paragraphs in previous revision for further analysis.
for paragraph_prev_hash in revision_prev.ordered_paragraphs:
for paragraph_prev in revision_prev.paragraphs[paragraph_prev_hash]:
if (not paragraph_prev.matched):
unmatched_paragraphs_prev.append(paragraph_prev)
return (unmatched_paragraphs_curr, unmatched_paragraphs_prev,
matched_paragraphs_prev)
def analyseParagraphsInRevision(revision_curr, revision_prev, text_curr):
# Containers for unmatched and matched paragraphs.
unmatched_paragraphs_curr = []
unmatched_paragraphs_prev = []
matched_paragraphs_prev = []
# Split the text of the current into paragraphs.
paragraphs = Text.splitIntoParagraphs(text_curr)
# Iterate over the paragraphs of the current version.
for paragraph in paragraphs:
# Build Paragraph structure and calculate hash value.
paragraph = paragraph.strip()
hash_curr = Text.calculateHash(paragraph)
matched_curr = False
# If the paragraph is in the previous revision,
# update the authorship information and mark both paragraphs as matched (also in HT).
if (hash_curr in revision_prev.ordered_paragraphs):
for paragraph_prev in revision_prev.paragraphs[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[
hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[
paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update(
{paragraph_prev.hash_value: [paragraph_prev]})
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
break
# If the paragraph is not in the previous revision, but it is in an older revision
# update the authorship information and mark both paragraphs as matched.
if ((not matched_curr) and (hash_curr in paragraphs_ht)):
for paragraph_prev in paragraphs_ht[hash_curr]:
if (not paragraph_prev.matched):
matched_curr = True
paragraph_prev.matched = True
matched_paragraphs_prev.append(paragraph_prev)
# TODO: added this (CHECK).
for hash_sentence_prev in paragraph_prev.sentences.keys():
for sentence_prev in paragraph_prev.sentences[
hash_sentence_prev]:
sentence_prev.matched = True
for word_prev in sentence_prev.words:
word_prev.matched = True
# Add paragraph to current revision.
if (hash_curr in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[
paragraph_prev.hash_value].append(paragraph_prev)
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
else:
revision_curr.paragraphs.update(
{paragraph_prev.hash_value: [paragraph_prev]})
revision_curr.ordered_paragraphs.append(
paragraph_prev.hash_value)
break
# If the paragraph did not match with previous revisions,
# add to container of unmatched paragraphs for further analysis.
if (not matched_curr):
paragraph_curr = Paragraph()
paragraph_curr.hash_value = Text.calculateHash(paragraph)
paragraph_curr.value = paragraph
revision_curr.ordered_paragraphs.append(paragraph_curr.hash_value)
if (paragraph_curr.hash_value in revision_curr.paragraphs.keys()):
revision_curr.paragraphs[paragraph_curr.hash_value].append(
paragraph_curr)
else:
revision_curr.paragraphs.update(
{paragraph_curr.hash_value: [paragraph_curr]})
unmatched_paragraphs_curr.append(paragraph_curr)
# Identify unmatched paragraphs in previous revision for further analysis.
for paragraph_prev_hash in revision_prev.ordered_paragraphs:
for paragraph_prev in revision_prev.paragraphs[paragraph_prev_hash]:
if (not paragraph_prev.matched):
unmatched_paragraphs_prev.append(paragraph_prev)
return (unmatched_paragraphs_curr, unmatched_paragraphs_prev,
matched_paragraphs_prev)
