From 2ca8d152058458857944e1c5e9f116fdb744a9c3 Mon Sep 17 00:00:00 2001
From: Malte Schokolowski <baw8441@uni-hamburg.de>
Date: Sat, 27 Nov 2021 15:30:26 +0100
Subject: [PATCH] added test functunality
---
verarbeitung/Processing.py | 81 +++++++++++-------
.../__pycache__/input_test.cpython-39.pyc | Bin 0 -> 2495 bytes
.../__pycache__/json_demo.cpython-39.pyc | Bin 805 -> 891 bytes
verarbeitung/input_test.py | 5 +-
verarbeitung/json_text.json | 2 +-
"verarbeitung/n\303\266tige Tests.txt" | 4 +
6 files changed, 61 insertions(+), 31 deletions(-)
create mode 100644 verarbeitung/__pycache__/input_test.cpython-39.pyc
create mode 100644 "verarbeitung/n\303\266tige Tests.txt"
diff --git a/verarbeitung/Processing.py b/verarbeitung/Processing.py
index 89f1ef2..ac85f52 100644
--- a/verarbeitung/Processing.py
+++ b/verarbeitung/Processing.py
@@ -25,9 +25,13 @@ from json_demo import output_to_json
# doi_input_list: list of publication dois from user
# TO-DO: Listenelemente auf Korrektheit überprüfen
-def initialize_nodes_list(doi_input_list):
+def initialize_nodes_list(doi_input_list, test_var):
for pub_doi in doi_input_list:
- pub = input_test_func(pub_doi)
+ if(test_var):
+ pub = input_test_func(pub_doi)
+ else:
+ pub = input(pub_doi)
+
not_in_nodes = True
for node in nodes: # checks if a pub is already in nodes
if (pub.doi_url == node.doi_url):
@@ -35,6 +39,7 @@ def initialize_nodes_list(doi_input_list):
break
if (not_in_nodes):
nodes.append(pub)
+ #print(pub.doi_url)
pub.group = "input"
else:
doi_input_list.remove(pub_doi)
@@ -55,11 +60,11 @@ def create_graph_structure_citations(pub, search_height, search_height_max):
if (search_height <= search_height_max):
citation.group = "height"
nodes.append(citation)
- edges.append([pub.doi_url,citation.doi_url])
+ edges.append([citation.doi_url,pub.doi_url])
# adds only edge if citation already exists
else:
- edges.append([pub.doi_url,citation.doi_url])
+ edges.append([citation.doi_url,pub.doi_url])
@@ -77,11 +82,11 @@ def create_graph_structure_references(pub, search_depth, search_depth_max):
if (search_depth <= search_depth_max):
reference.group = "depth"
nodes.append(reference)
- edges.append([reference.doi_url,pub.doi_url])
+ edges.append([pub.doi_url,reference.doi_url])
# adds only edge if citation already exists
else:
- edges.append([reference.doi_url,pub.doi_url])
+ edges.append([pub.doi_url,reference.doi_url])
@@ -89,13 +94,17 @@ def create_graph_structure_references(pub, search_depth, search_depth_max):
# doi_citations: input list of citet dois
# search_height: current search_height of height-first-search
# search_height_max: maximal search_height for dfs
-def process_citations_rec(doi_citations, search_height, search_height_max):
+def process_citations_rec(doi_citations, search_height, search_height_max, test_var):
# height of search is increased by 1 with each recursive call
search_height += 1
# create class object for every citation from list
for pub_doi in doi_citations:
- pub = input_test_func(pub_doi)
+ if (test_var):
+ pub = input_test_func(pub_doi)
+ else:
+ pub = input(pub_doi)
+
create_graph_structure_citations(pub, search_height, search_height_max)
# If the maximum height has not yet been reached, all references from the publication
# are written to an array and the function is called again with this array.
@@ -109,7 +118,7 @@ def process_citations_rec(doi_citations, search_height, search_height_max):
citations_list.append(citation.doi_url)
# recursive call of function.
- process_citations_rec(citations_list, search_height, search_height_max)
+ process_citations_rec(citations_list, search_height, search_height_max, test_var)
@@ -117,13 +126,17 @@ def process_citations_rec(doi_citations, search_height, search_height_max):
# doi_references: input list of referenced dois
# search_depth: current search_depth of height-first-search
# search_depth_max: maximal search_depth for dfs
-def process_references_rec(doi_references, search_depth, search_depth_max):
+def process_references_rec(doi_references, search_depth, search_depth_max, test_var):
# The depth is increased by 1 with each recursive call
search_depth += 1
# create class object for every citation from list
for pub_doi in doi_references:
- pub = input_test_func(pub_doi)
+ if (test_var):
+ pub = input_test_func(pub_doi)
+ else:
+ pub = input(pub_doi)
+
create_graph_structure_references(pub, search_depth, search_depth_max)
# If the maximum depth has not yet been reached, all references from the publication
# are written to an array and the function is called again with this array.
@@ -133,16 +146,17 @@ def process_references_rec(doi_references, search_depth, search_depth_max):
# currently only the references with acs are stored in the URL, because we can't
# extract the info from other sources.
- if ("acs" in reference.doi_url):
+ if ("acs" in reference.doi_url or test_var == True):
references_list.append(reference.doi_url)
+
# recursive call of function.
- process_references_rec(references_list, search_depth, search_depth_max)
+ process_references_rec(references_list, search_depth, search_depth_max, test_var)
-def process_main(doi_input_list, search_height, search_depth):
+def process_main(doi_input_list, search_height, search_depth, test_var = False):
# ERROR-Handling doi_array = NULL
if (len(doi_input_list) == 0):
print("Error, no input data")
@@ -161,16 +175,33 @@ def process_main(doi_input_list, search_height, search_depth):
nodes = []
edges = []
- initialize_nodes_list(doi_input_list)
- process_citations_rec(doi_input_list, 0, search_height)
- process_references_rec(doi_input_list, 0, search_depth)
+ initialize_nodes_list(doi_input_list,test_var)
+ process_citations_rec(doi_input_list, 0, search_height, test_var)
+ process_references_rec(doi_input_list, 0, search_depth, test_var)
output_to_json(nodes,edges)
# only for internal testing
return(nodes,edges)
+def print_graph(nodes, edges):
+ print("Knoten:\n")
+ for node in nodes:
+ print(node.title, "\n")
+ print("\n Kanten:\n")
+ for edge in edges:
+ print(edge,"\n")
+
+
+# function to test cycles
+def test_cycle():
+ arr = []
+ arr.append('doiz1')
+ #arr.append('doiz2')
+ nodes,edges = process_main(arr,1,1,True)
+
+ print_graph(nodes, edges)
# program test, because there is no connection to the input yet.
def test_print():
@@ -185,19 +216,11 @@ def test_print():
#url = sys.argv[1]
#arr.append[url]
- arr.append('doi1')
- #arr.append('doi2')
- #arr.append('doi3')
-
- nodes,edges = process_main(arr,1,1)
+ nodes,edges = process_main(arr,2,2,True)
- print("Knoten:\n")
- for node in nodes:
- print(node.title, "\n")
- print("\n Kanten:\n")
- for edge in edges:
- print(edge,"\n")
+ print_graph(nodes, edges)
-test_print()
+#test_print()
+test_cycle()
\ No newline at end of file
diff --git a/verarbeitung/__pycache__/input_test.cpython-39.pyc b/verarbeitung/__pycache__/input_test.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..d5948ff804073098a6d097ad17e81503eb7ec86b
GIT binary patch
literal 2495
zcmcgt&2HO95Z>kQQkG@eaT42c+Qw;;s(=NE0(uCFHh=@9mkL3Q00p6fpgFX_n33cq
zS-=8)avr4ZO)t^M=z-Us^a?$7X7yvqL4qPEN@2d;+1VY<%+AgP>+2PU-`@AX2Y)z>
z{YA|3Cy;rDl>UkEf&l~m4(Uqsh|@qvPDhR-XMl;EiJS%&*zcI9g8&Cd11hkFqX|`5
zhgy%r2Gn5_$1S8=J>glf3EOZRxjS&T$Dle}w_yu*U>CVPxJRofqx}N*;XZr@pZ7HQ
z0v^Bt?jRzW0|)RBzJy08dkjxtAJ>UUR*9_0jzr`{m7eLX!B@wu(FoDEl}|(N8B)59
z5HXJfL!UTk$|oJq80Ff_{3MCPAd3h65JR{4Xif@_kkT$f!3*ZILPO+*j;Iv|qF$JY
zMqvTVnQZnLa%R7hS%q~)C(OcDk{^`BMu{kFC9w;EatGKk8}m-1Qra+x{ahxcnZ;QW
zmDO<2&t!a(X9Jm*_M1U2`$1CHhu0?i5M)tVk<n=+qkb5rrH=E`3FAz;ggj15vnL1n
zu;G+O8YQPvM|Y$_U=mmaHUZ^{q*RhsgfWvf9R5BIpLSoTkxaWk21yomU&LAWC_X-X
zDF<(&v#cA&hw0&P${hX@$v~b&ahCUc-4!P85A)2=qBLs`FG}J2aX-#{pMsq3ATVw%
zeu4|F!lyXeUb>^^{8(pfkdA)vHuC+l;`?t0kS8>+`u=$yBvXm3qhjU85^T^Kr+-9B
z$pFC>|4At%j%L9QDUkDz=8OC}K<4B5Ls=kc|JeNC^^7gKjypamzv&^lPN|=&;;@MA
zXmf7xbui^7DW=<A0u`p)xOR(_%)&(cCxyv*HBZw2Bu?@U8GD!D+H7SpxxJ5c)9tN=
z0sqEt%E)`9W#%{WA?3^bqerxcbcB@tgpjf4?B~uUKKg<K-(_c-G%`M&BWk;}t}8SY
znhGt2wnDMXuEeEQXd0&GF*`RXEgDW|g6i3X{(VB`Oz6KS^nfSyfG3n|6MDc6t*j++
zn)!oMKaeuGNL5-l^wP$n;bVO%O|@R?$lnNDxpDnM{nNZ3K17Wvl>~+_vC6;U@)6Eg
zf<QJbg76BN9-{zYAf8`pDj-iUb*!2CEFkrQ|H`u&kE;|ET?Iu43W^RGlq>T$&e?hW
zTofE@qt%hSs9Ek2(3MEKU3nj2tjh;DlvXetMtzW!oLJO_iUE4-8Cd<&>4PC}Zg?!o
z^skXpDtC+<RB_PLCRdXG+f(@%jgU_e8is7(;2BuVKVm-hC>QB{^GSmJdJwlfOEr_0
zx7<xyo|tu$7It%NAuYApRoE`s?2x;1$Xy(Ar-$6xw)V=l_F`Lmx~*NBXvnDL*~*ep
zYqYV{*ha19dke1T%*?}67TJfRQsT~)xT{Lsn@Zf~k`gpjDRDcEs(KJAQ6xQSmD1|A
zrHYw@tt%bIQPT1jQ`9tHZF~0U;w;Hi^kzD7RR%64ma0Znh)VJ8v?qP1+6>jJ+Ez`}
Sgs_DW&K}?4JK8?q*Zu)Q#0aqf
literal 0
HcmV?d00001
diff --git a/verarbeitung/__pycache__/json_demo.cpython-39.pyc b/verarbeitung/__pycache__/json_demo.cpython-39.pyc
index 29c2c14b5229d9768c2a273f8e1adba6cfcfc63f..a4f37b5097c0c5a82e7d36cd45671fb178e749ca 100644
GIT binary patch
delta 379
zcmYk2zfQw25XOCp<2Y$rx**X%3?L*_BqZ27Ga@7g)Gm?11rkD1OfnQ1F;vVbiePRL
zJO?}lLuTHBg-aH=Px|h6pKtNKvme$H&8ADR-gaMwP4m_jeCKyvILe>5H>}XoOwu9I
zR>+X7nrtM7WGs08(Rr{tM03e8u%%P8i)=2q=1Tx_6KO+J*{Cw?-jJk@Y|7T$c<SFf
zsk>-ss-2|)<b+5<QF9YW+}<a*UwZ^<jnE}ICWDp3lE&hCGG-!6FB4VL+1f;?(hieM
z#UdJ;G6_oSLM7R>7{L&{;srLh+SBYb3eH3tB(X0=I#Cw>xU_NE&s3xsPQ@oYLa#V5
zB7dj42e4Wk-TfyIs>G|sfg2vEb=)3MwTi9eK|IY;|2$L%j`fr3RrF{5qG5J_0q9v%
AZvX%Q
delta 293
zcmYL@y-ve06ov1#9mg?gRi=`P2_d0wz?^63!hqVPiewOhl7LB;%7~$2M97NDoDRGJ
z15d!fBUIu^Sa7^>k95v=e}?<Z-+4dl^(44jrZ)Sawts_Pb~(aRyFQ|%4eU?y#1b$<
z1u2+NanGS++6G2!5aE7eh+#@}GnY{c6<1R2tjO#BV^oE$Fw8_7f^ZHBnA3_P6oV6Z
z_&f&mnmSi-2IF|LWkq&-G2>ZXU6p!96)E%P1yhWgZ#)p8D)V`*7tMe?<FI)ni|Jwa
wKXNbOT%sfrW9&Hg5-3QFI&pVnrgvRzMPA(1)%@~W6W98c9(MF^drd}1f1-Fg`~Uy|
diff --git a/verarbeitung/input_test.py b/verarbeitung/input_test.py
index 79b00b1..c55f852 100644
--- a/verarbeitung/input_test.py
+++ b/verarbeitung/input_test.py
@@ -60,4 +60,7 @@ beispiel1 = ['doi1', 'title1', ['contributor1'], 'journal1', 'date1', ['doi2'],
beispiel2 = ['doi2', 'title2', ['contributor2'], 'journal2', 'date2', [], ['doi1'], '']
beispiel3 = ['doi3', 'title3', ['contributor3'], 'journal3', 'date3', ['doi1'], [], '']
-list_of_arrays = [beispiel1, beispiel2, beispiel3]
+zyklus1 = ['doiz1', 'titlez1', ['contributorz1.1', 'contributorz1.2'], 'journalz1', 'datez1', ['doiz2'], ['doiz2'], '']
+zyklus2 = ['doiz2', 'titlez2', ['contributorz2.1', 'contributorz2.2'], 'journalz2', 'datez2', ['doiz1'], ['doiz1'], '']
+
+list_of_arrays = [beispiel1, beispiel2, beispiel3, zyklus1, zyklus2]
diff --git a/verarbeitung/json_text.json b/verarbeitung/json_text.json
index 683e49f..8f648bf 100644
--- a/verarbeitung/json_text.json
+++ b/verarbeitung/json_text.json
@@ -1 +1 @@
-{"nodes": [{"name": "title1", "author": ["contributor1"], "year": "date1", "journal": "journal1", "doi": "doi1", "group": "input"}, {"name": "title3", "author": ["contributor3"], "year": "date3", "journal": "journal3", "doi": "doi3", "group": "height"}, {"name": "title2", "author": ["contributor2"], "year": "date2", "journal": "journal2", "doi": "doi2", "group": "depth"}], "links": [{"source": "doi1", "target": "doi3"}, {"source": "doi2", "target": "doi1"}]}
\ No newline at end of file
+{"nodes": [{"name": "titlez1", "author": ["contributorz1.1", "contributorz1.2"], "year": "datez1", "journal": "journalz1", "doi": "doiz1", "group": "input"}, {"name": "titlez2", "author": ["contributorz2.1", "contributorz2.2"], "year": "datez2", "journal": "journalz2", "doi": "doiz2", "group": "depth"}], "links": [{"source": "doiz1", "target": "doiz2"}]}
\ No newline at end of file
diff --git "a/verarbeitung/n\303\266tige Tests.txt" "b/verarbeitung/n\303\266tige Tests.txt"
new file mode 100644
index 0000000..9556328
--- /dev/null
+++ "b/verarbeitung/n\303\266tige Tests.txt"
@@ -0,0 +1,4 @@
+Zyklus
+großer Zyklus
+Innere Kanten vervollständigen
+
--
GitLab