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
zcmYe~<>g{vU|^84UzE6ylY!weh=Ytd7#J8F7#J9euQ4z%xHF_Mq%gKHq%bx!MS*xs
zDa<VlDa_4GQH<^kDJ&_hEet8F%}h~DDQqe1Eeui2DI6)BEeugCDO@SsEeuhtDLg5>
zDSYXSDf}q{DT3*YDMIOtDZ=R-QEVxKDIzJN>5M62DdOo2DLhbd_7tHMi4@6n#uTX(
zX^?0-16VyricE@Zid>3(I#Y^5ieidVIwKf^%;HQ@N>NTxNl{H_N>NKuPmxJy1Y?jK
zS1Ma7dn!jNXDU}ZYZP~iMlge>W-_vmL2M?NuSFOb7*ZLc7*iOcm{J&1n81Ew4rb6~
zxy2n&nv|27oLG{XpO?%D(gnpJHpl>HP_V@?Ffi0G)-c2~)G*aB#52|~*D%C0)v(ks
z#532h)-c4g)Uc&6lrj|Qr8Cqp#Ixpcm9W*YHG_1p*06(RJis#Sd0ZtNHSAy+_8N{F
zhIq~thG2%3jDDJ2x7btiGviB(a&EDfWR~Ql-r`Bl&nqd)Oe!tOFDkypo|Ru(l$V%u
zOP~PZ<oJ}tlGIyVMX712MX7nosl~ULi&E2WaVBS$fW1_Fi#a*7<Q8jsQGRKGCg&}d
z;?$h9B4!2#h9VXa!3rYSKm<F80Hu>6P*N)5VPIfb$xy_{z`*b;IN2&Dv^ce>IL0?I
zrzADTJ+manIWt%{peR2pHM=AxIa9Y-w*bP?ElVv*EJ{kvEGf-Pk3r#N<`tBd#FwNN
zm*^E#-r|Ul&&<m#iH`>ba<K#`)EU{}kb{wfiHi|JR*4|RkseH&-%1vc8F`7hsqyi*
zxZ>k;^HWN5Ky04)_`=e}9EePj0LWh;Z-D&*A^1UJj0_A6AY2S`00(0ch)q@!;&6rr
zb}}d+K^_5N5F2DNIQ=LQOh2GhPy|xHk`-t4tYj<V1-Tq&^dY<n_94jYprl_6icto5
z*j5R`9E=FeB0-SB2>oCd*bq?$1_ohJ9soIxgRuz2Co7mZgJ6l2D&bTl26C}DhyXhl
zOn_Ys^0o}f#c19Zf;)g1e}ht_G{_XFzd`(DP#OV6E(n8Sft!JW0UW^*3=9k<3@!|@
zezlA>3^j}?jFJr5Ohqguj1YDWV+xZbNSql=vVcieFv$ic*})`-BttVtEmI8>69Xed
zFhd~=C|PK7`n?2M_!4CMOOSJ3g6w_?%D^u{8TchAt-S<gU`?i5d^wrLCGq)b@rgx6
ziIv6RWUa}3i@l&UDLy4X^A;;u{1$UTX%Zwezyt0UKO%?5r<LX<D}%fbDiRnNIT(2u
z%@~VR85kH)0s-U(cpwBZFfgPufC9jUA=agq2^=6+wahh4HO$Ze5vXBYz*qw1*D!+v
zg*gQjD9kCKKw(Z{m1JmUUC7ADP$*EyQNtL_u#(NMND>syQXm2pB}JgvEs_P5P|QV&
z3=9mn*b)m0Qu9*4iBps176&*CQt~sSSdueKiXj;a<Qp^}7lE9v1@a}RxMN^s0hKt6
zJdApbU>SP*v`7u)Lv;oQ22GYCO$G*rD3+qsG(67dWME)0!s>jGOcYB>ex_j*8@Mtt
zj6$wW45K)pwTWRAE2s)F1S>WIlg76gpqh+OG#SA)89_7|L6sS!C^LpDGlnQLzQvl7
zpIK!X#SV5!m0=Y>QpHwfsD~k76vYX3UX@`K8_0cCAa~|xRvEzzF+w%O2;C4PJtRYn
zpoSRvY4U(G1UR7-fwD9>NrPj%2pnddNvWB|1(~TihEZ^)5rSzP#a>mJol{zD2xAz5
tQy@~pLgXh78%UjG2g<m`pz?}Oh>wGhgM*!egM(9wQG!u|Nrq8|2>?RG2(bVF
literal 0
HcmV?d00001
diff --git a/verarbeitung/__pycache__/json_demo.cpython-39.pyc b/verarbeitung/__pycache__/json_demo.cpython-39.pyc
index 29c2c14b5229d9768c2a273f8e1adba6cfcfc63f..a4f37b5097c0c5a82e7d36cd45671fb178e749ca 100644
GIT binary patch
delta 379
zcmZ3=_M43_k(ZZ?fq{WxiSD9Ac9w~J*^EynR!K1iOq{B&$eP7k!<NEg!%)MT#a6?X
z!U|@w*RZ9q*)Y^FE#R2AU$UNElA(qpg~NuShCPK7%;vITs9|2fQNyv2k&&S=r-rG9
zC50O#R>P9QW5ZCwnZldG*UZ!}Q_ESxwSc>ZrG|4M6C*=7Lka^60}DelGb2NufFVQi
zH3J4lFpOkiWJqBMX3*sKyTy{1n422KmRMSnkzaI+rBWg_vFH|iR(@$wUSduZb4q^Z
zE!Om+{L+HSk&HHsJd>v}Dyaw*lqTh5CMT9;=I6zyB$lKWu`)0)++t73&x|iE$|+)F
zU|^VhfU%WPda@f+PP`T<JQ&%)kb{wpkqZg(FoHyQ7(tMOk%Nhcu}GGIfkBg{NEBow
eM`m6@X-RxqRuK~e0|Qv9NE*aK5HgdwnWX^eSyOKS
delta 293
zcmey(wv>%8k(ZZ?fq{Xc%4TBX7Uqe3*^I{~R!K1$O`NLE%(Q@Y;$6vl7D<L0juciK
zh8p%1HZYsrhM|Ue0c#D%LPkc0LcbcO8kQ6ekXQ{%3a1T230n$R3U@P8zf3J>3Ht($
z8kQQ)g-nbL;S4DZEDS6R&CHApc>;zE#XAfb7{M@-fsrAFA(%mv$L|(PUSe))6kB3x
zNk)EA6mtqwe&*y}MjJ-X$)^~VIM`G2GviB(awZEfwK9rNp2n0DsRD98BO4fUFtRan
zF>*0+G4e2i*gT9N$ic|L#KTx5$-uy%$x<Z9z`$^eBQvj{v?M+)tB8q#fdMR4Bo1OB
K2#Lvw%u)cNcsl$5
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