yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-12-26 22:55:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(biomed connector): added additional params (#468) (#623)

Browse Source 
Unstructured-ingest biomed connector: Adds max retries, max request time with backoff and decay.

---------

Co-authored-by: Crag Wolfe <crag@unstructuredai.io>
This commit is contained in:
kravetsmic 2023-06-15 11:57:45 +03:00 committed by GitHub
parent e0c477de68
commit 7fd7d7afae
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
12 changed files with 3839 additions and 283 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.md
View File

@ -1,7 +1,9 @@
## 0.7.6-dev0
## 0.7.6-dev1
### Enhancements
* Adds retry logic for the unstructured-ingest Biomed connector
### Features
* Updates `partition_docx` to include headers and footers in the output.

572
test_unstructured_ingest/expected-structured-output/biomed-ingest-output-api/65/11/main.PMC6312790.pdf.json
View File

@ -4,6 +4,18 @@
"text": "Contents lists available at ScienceDirect Data in Brief journal homepage: www.elsevier.com/locate/dib",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "0ca3f075fdccf9232449ff461b63ceb9",
"text": "journal homepage: www.elsevier.com/locate/dib",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -12,14 +24,18 @@
"text": "Data on environmental sustainable corrosion inhibitor for stainless steel in aggressive environment",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "2f1fc1e2cafb608e60f5bd42de4ae4e3",
"text": "Omotayo Sanni , Abimbola Patricia I. Popoola",
"element_id": "5785aecdfd5bc21339f3c9d9f12c304f",
"text": "Sanni , Abimbola Patricia I. Popoola",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -28,14 +44,18 @@
"text": "Department of Chemical, Metallurgical and Materials Engineering, Tshwane University of Pretoria, South Africa",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "46b25f5727bf94442e3830943529dba3",
"text": "This data article contains data related to the research article entitled “enhanced corrosion resistance of stainless steel Type 316 in sulphuric acid solution using eco-friendly waste product” (Sanni et al., 2018). In this data article, a comprehensive effect of waste product and optimized process parameter of the inhibitor in 0.5M H SO solution was presented using weight loss and potentiody- 2 4 namic polarization techniques. The presence of the inhibitor (egg shell powder) influenced corrosion resistance of stainless steel. Inhibition efficiency value of 94.74% was recorded as a result of inhibition of the steel by the ionized molecules of the inhibiting compound of the egg shell powder influencing the redox mechan- ism reactions responsible for corrosion and surface deterioration.",
"element_id": "66fd3262abfb07b2f7c2f8f29b69be94",
"text": "This data article contains data related to the research article entitled “enhanced corrosion resistance of stainless steel Type 316 in sulphuric acid solution using eco-friendly waste product” (Sanni et al., 2018). In this data article, a comprehensive effect of waste product and optimized process parameter of the inhibitor in 0.5M H SO solution was presented using weight loss and potentiody- 2 4 namic polarization techniques. The presence of the inhibitor (egg shell powder) influenced corrosion resistance of stainless steel. Inhibition efficiency value of 94.74% was recorded as a result of inhibition of the steel by the ionized molecules of the inhibiting compound of the egg shell powder influencing the redox mechan- ism reactions responsible for corrosion and surface deterioration.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -44,38 +64,48 @@
"text": "& 2018 Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "3ec82e9a5e3b39e7710305fd9be4e8d5",
"text": "(http: ||creativecommons. org/licenses/by- nc- -nd/4, 0/).",
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
"text": "",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "83c3591fd4eb7080544beb6439b16253",
"text": "Subject area Materials engineering More specific subject area Surface science and engineering Type of data Table and figure",
"element_id": "188408ad3575b107d0af4a0133f1a1b5",
"text": "Subject area Materials engineering More specific subject area Surface science and engineering Type of data Table and figure",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "a99ce2b3a3248e3520d501ca1d5cd565",
"text": "n Corresponding author. tayo.sanni@yahoo.com; E-mail address: tayo.sanni@yahoo.com (O. Sanni).",
"element_id": "55c108022a3b82a047cc24812bc106d1",
"text": "n Corresponding author. tayo.sanni@yahoo.com; SanniO@tut.ac.za E-mail address: tayo.sanni@yahoo.com (O. Sanni).",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "f7c575292a9d9f0d9d8653435e5d43e1",
"text": "2352-3409/& 2018 Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).",
"element_id": "30b5af6114bd8cea03b625ca89fa87ae",
"text": "2352-3409/& 2018 Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND (http://creativecommons.org/licenses/by-nc-nd/4.0/).",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -84,6 +114,8 @@
"text": "The cleaned and weighed specimen was suspended in beakers con- taining",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -92,6 +124,8 @@
"text": "M H SO solution of different concentrations of egg shell",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -100,14 +134,18 @@
"text": "powder. The pre-weighed stainless steel samples were retrieved from the test solutions after every",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "24d492516b518511d328f13a30d7b86a",
"text": "h, cleaned appropriately, dried and reweighed. Raw, analyzed The difference between the weight at a given time and the initial weight of the specimen was taken as the weight loss, which was used to calculate the corrosion rate and inhibition efficiency. Inhibitor concentration, exposure time Department of Chemical, Metallurgical and Materials Engineering, Tshwane University of Technology, Pretoria, South Africa Data are available within this article O. Sanni, A. P. I. Popoola, and O. S. I. Fayomi, Enhanced corrosion resistance of stainless steel type",
"element_id": "6209f3b19e07552860684157149e843d",
"text": "h, cleaned appropriately, dried and reweighed. Raw, analyzed The difference between the weight at a given time and the initial weight of the specimen was taken as the weight loss, which was used to calculate the corrosion rate and inhibition efficiency. Inhibitor concentration, exposure time Department of Chemical, Metallurgical and Materials Engineering, Tshwane University of Technology, Pretoria, South Africa Data are available within this article O. Sanni, A. P. I. Popoola, and O. S. I. Fayomi, Enhanced corrosion resistance of stainless steel type",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -116,6 +154,8 @@
"text": "in sulphuric acid solution using eco-friendly waste product, Results in Physics,",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -124,6 +164,8 @@
"text": "(",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -132,6 +174,8 @@
"text": ")",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -140,6 +184,8 @@
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -148,22 +194,18 @@
"text": "O. Sanni, A. P. I. Popoola, and O. S. I. Fayomi, Enhanced corrosion resistance of stainless steel type 316 in sulphuric acid solution using eco-friendly waste product, Results in Physics, 9 (2018) 225–230.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "596eda178f8c5adefbae7cfe1bec78c3",
"text": "Value of the data",
"type": "Title",
"metadata": {
"page_number": 2
}
},
{
"element_id": "e2f2e340a83cb4119bb5909ec7b5f612",
"text": "Data presented here provide optimum conditions of waste material as inhibitor for stainless steel Type",
"element_id": "19797594cb4854994d4a2a1aa1cf0a22",
"text": "Data presented here provide optimum conditions of waste material as inhibitor for stainless Type",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -172,14 +214,18 @@
"text": "in",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "264c03cc398a68c5d4640a81555ce482",
"text": "M H SO medium. The given data describe the inhibitive performance of",
"element_id": "ce0d7237d1165496994a7bb44455523c",
"text": "M H SO medium. The given data describe the inhibitive performance",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -188,54 +234,48 @@
"text": "eco-friendly egg shell powder on austenitic stainless steel Type",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "23be275a9ce00cdf1706d62e73b91aa9",
"text": "corrosion in sulphuric acid environment. (cid:",
"element_id": "6f5bb709b99bde79a1fe84ae401e09db",
"text": "corrosion in sulphuric environment. The data obtained for the inhibition of waste product (egg shell powder) on stainless steel Type can be used as basis in determining the inhibitive performance of the same inhibitor in environments. The data can be used to examine the relationship between the process variable as it affect nature of inhibition of metals.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "0665141237fc45446e526d71b3668950",
"text": ") The data obtained for the inhibition of waste product (egg shell powder) on stainless steel Type",
"type": "ListItem",
"element_id": "c2b2b778d53cc9a1cb4dc340476bc5aa",
"text": "1. Data",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "13dbe1cc5fb724b70d0871aff0de4284",
"text": "can be used as basis in determining the inhibitive performance of the same inhibitor in other environments. (cid:",
"type": "ListItem",
"metadata": {
"page_number": 2
}
},
{
"element_id": "bb742e913a5609d298f92e9ea470d82b",
"text": ") The data can be used to examine the relationship between the process variable as it affect the nature of inhibition of metals.",
"type": "ListItem",
"metadata": {
"page_number": 2
}
},
{
"element_id": "6bcf0a940a926451afde639adcd496df",
"text": "The results of the experiment are presented in this session. The results obtained from weight loss method for stainless steel Type 316 immersed in 0.5 M H SO solution in the absence and presence of 2 4 different concentrations of egg shell powder (ES) are presented in Figs.1–3 respectively. It can be seen clearly from these Figures that the efficiency of egg shell powder increase with the inhibitor con- centration, The increase in its efficiency could be as a result of increase in the constituent molecule",
"element_id": "07a004d6f4e4bd2c46007345c5ee4366",
"text": "The results of the experiment are presented in this session. The results obtained from weight loss method for stainless steel Type 316 immersed in 0.5 M H SO solution in the absence and presence of 2 4 different concentrations of egg shell powder (ES) are presented in Figs.1–3 respectively. It can be seen clearly from these Figures that the efficiency of egg shell powder increase with the inhibitor con- centration, The increase in its efficiency could be as a result of increase in the constituent molecule",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "c01b75d5cbf72a487d08a6fdc1124ecc",
"text": "30 10g8g6g4g 20 2gControl 10 48 96 144 192 Exposure Time (Hours) )gm( ssol thgieW",
"element_id": "07c6b69c966def662fa029b16ddb0f82",
"text": "30 10g 8g 6g 4g 20 2g Control 10 48 96 144 192 )gm( ssol thgieW",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -244,14 +284,18 @@
"text": "Fig. 1. Weight loss versus exposure time for stainless steel immersed in 0.5M H SO solution in the absence and 2 4 presence of ES.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "b88069046b221cfeaca20663d9c05796",
"text": "2.7 1.8 10g8g6g4g 0.9 2gControl 24 48 72 96 120 144 168 192 Exposure time )raey/mm( etar noisorroC",
"element_id": "034ae8b8c3ffe3e43982c90c256e715d",
"text": "2.7 1.8 10g 8g 6g 4g 0.9 2g Control 24 48 72 96 120 144 168 192 Exposure time )raey/mm( etar",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
@ -260,46 +304,48 @@
"text": "Fig. 2. Corrosion rate versus exposure time for stainless steel immersed in 0.5M H SO solution in the absence and 2 4 presence of ES.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "8d33af7293de42bec81d4024b3c46ae1",
"text": "90 2g 80 4g6g 70 8g10g 60 50 40 30 20 10 0 20 40 60 80 100 120 140 160 180 Exposure Time (Hours) )%( ycneiciffE noitibihnI",
"element_id": "5076ebbaf4279d1f9a203f6a764eed11",
"text": "90 2g 80 4g 6g 70 8g 10g 60 50 40 30 20 10 0 20 40 60 80 100 120 140 160 180 Exposure Time (Hours) ycneiciffE noitibihnI",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "6fb077550ac04cbe69d234ec1a6c3be1",
"text": "Fig. 3. Inhibition efficiency versus exposure time for stainless steel immersed in 0.5M H SO solution in the presence of ES. 2 4",
"element_id": "afcbce1b85aa91bf323b6ac63768719d",
"text": "Fig. 3. Inhibition efficiency versus exposure time for stainless steel immersed in 0.5M H SO solution in the presence of ES. 2 4",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "7ce9fd00a344badbddae732f83f7317d",
"text": "active sites of the stainless steel to be protected with the inhibitor molecules. Cathodic and anodic polarized potential are measured in the presence and absence of ES. Fig. 4 shows the cathodic and anodic polarization curves for stainless steel in 0.5 M H SO solution at different ES concentrations. 2 4 The electrochemical variables such as polarization resistance (PR), corrosion potential (Ecorr), cor- rosion current (icorr), anodic Tafel constant (ba), cathodic Tafel constant (bc) and corrosion rate (mm/ year) values are presented in Table 1. From the polarization curves and electrochemical parameter, icorr value decreased with the addition of inhibitor in 0.5 M H SO . Conversely, the icorr further 2 4 decrease with an increase in inhibitor concentration indicating that the inhibition effects increase with an increase in the egg shell concentration. The process of egg shell inhibition could be attributed to the formation of egg shell powder adsorbed on stainless steel surface protecting corrosion of stainless steel in H SO medium. The likely mechanism is the egg shell adsorption on stainless steel 2 4 surface through the heteroatoms electron pair and the conjugated systems in egg shell molecular structure as shown in Fig. 1. When the concentration of inhibitor was increased from 2 to 10 g, the corrosion rate values drastically decreased this result show that waste egg shell powder is an effective corrosion inhibitor for stainless steel in H SO solution. The shift in corrosion potential of stainless 2 4 steel from Tafel curves and electrochemical data indicate that the inhibitor is a mixed-type corrosion inhibitor.",
"element_id": "876206f2f8dc52f8c7e1a49620eb79a2",
"text": "active sites of the stainless steel to be protected with the inhibitor molecules. Cathodic and anodic polarized potential are measured in the presence and absence of ES. Fig. 4 shows the cathodic and anodic polarization curves for stainless steel in 0.5 M H SO solution at different ES concentrations. 2 4 The electrochemical variables such as polarization resistance (PR), corrosion potential (Ecorr), cor- rosion current (icorr), anodic Tafel constant (ba), cathodic Tafel constant (bc) and corrosion rate (mm/ year) values are presented in Table 1. From the polarization curves and electrochemical parameter, icorr value decreased with the addition of inhibitor in 0.5 M H SO . Conversely, the icorr further 2 4 decrease with an increase in inhibitor concentration indicating that the inhibition effects increase with an increase in the egg shell concentration. The process of egg shell inhibition could be attributed to the formation of egg shell powder adsorbed on stainless steel surface protecting corrosion of stainless steel in H SO medium. The likely mechanism is the egg shell adsorption on stainless steel 2 4 surface through the heteroatoms electron pair and the conjugated systems in egg shell molecular structure as shown in Fig. 1. When the concentration of inhibitor was increased from 2 to 10 g, the corrosion rate values drastically decreased this result show that waste egg shell powder is an effective corrosion inhibitor for stainless steel in H SO solution. The shift in corrosion potential of stainless 2 4 steel from Tafel curves and electrochemical data indicate that the inhibitor is a mixed-type corrosion",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "07e8e4f9666bde08d71c1617f69eddd1",
"text": "Potential (Vv)nm°in°}ary=ES 724250.0000001T T T0.00001 0.001 olCurrent Density (A/cm2)",
"element_id": "b5ee6af3d776b0bbd2e581a3ab2ab2e1",
"text": "Potential (Vv)nm°in°}aryT T T0.00001 0.001 olCurrent Density (A/cm2)",
"type": "FigureCaption",
"metadata": {
"page_number": 4
}
},
{
"element_id": "edad5b9fb479e5aaa5337d03f6fb602f",
"text": "Fig. 4. Anodic and cathodic polarization curve of stainless steel in 0.5M H SO solution in the presence and absence of ES. 2 4",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -308,14 +354,18 @@
"text": "Potentiodynamic polarization data for stainless steel in the absence and presence of ES in 0.5M H SO solution. 2 4",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
{
"element_id": "aaea2e2509e619b587609ec31b8bdeb6",
"text": "Inhibitor bc (V/dec) ba (V/dec) Ecorr (V) icorr (A/cm2) Polarization Corrosion concentration (g) resistance (Ω) rate (mm/year) 0 0.0335 0.0409 (cid:3)0.9393 0.0003 24.0910 2.8163 2 1.9460 0.0596 (cid:3)0.8276 0.0002 121.440 1.5054 4 0.0163 0.2369 (cid:3)0.8825 0.0001 42.121 0.9476 6 0.3233 0.0540 (cid:3)0.8027 5.39E-05 373.180 0.4318 8 0.1240 0.0556 (cid:3)0.5896 5.46E-05 305.650 0.3772 10 0.0382 0.0086 (cid:3)0.5356 1.24E-05 246.080 0.0919",
"type": "UncategorizedText",
"type": "Table",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -324,6 +374,8 @@
"text": "The plot of inhibitor concentration over degree of surface coverage versus inhibitor concentration gives a straight line as shown in Fig. 5. The strong correlation reveals that egg shell adsorption on stainless surface in 0.5 M H SO follow Langmuir adsorption isotherm. Figs. 6–8 show the SEM/EDX 2 4 surface morphology analysis of stainless steel. Figs. 7 and 8 are the SEM/EDX images of the stainless steel specimens without and with inhibitor after weight loss experiment in sulphuric acid medium. The stainless steel surface corrosion product layer in the absence of inhibitor was porous and as a result gives no corrosion protection. With the presence of ES, corrosion damage was minimized, with an evidence of ES present on the metal surface as shown in Fig. 8.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -332,6 +384,8 @@
"text": "C/0 12 10 8 6 4 2 2 4 6 8 10 Concentration (g) 0/C",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -340,6 +394,8 @@
"text": "Fig. 5. Langmuir adsorption isotherm of ES.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -348,6 +404,8 @@
"text": "SEM HV: Q0KY WD: 14.89 rmrm‘DEM MAO: 209 x Det: DOE Pecforsence In nenospact",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 5
}
},
@ -356,14 +414,18 @@
"text": "Fig. 6. SEM/EDX image of as-received stainless steel.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 5
}
},
{
"element_id": "b0a40261108ea21c6136d3172b4cd987",
"text": "gEOOfeSem ny. 200 Rv",
"element_id": "4f8c25cf7aefbef4af474fe62bed2b33",
"text": "gEoswaeSem ny. 200 RvLitt td vegas rescanFertormarce innancesacel",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 5
}
},
@ -372,14 +434,18 @@
"text": "Fig. 7. SEM/EDX image of stainless steel immersed in 0.5M H SO solution without inhibitor. 2 4",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 5
}
},
{
"element_id": "bb1b80b1cdf7f88847e1c8231fb4aae7",
"text": "aSEM HY: 20.0KV",
"element_id": "035c30f23285fdae72335b94421cf564",
"text": "°@¢Naafe«MgsSEM HY: 20.0KV ALEC CMT LPL LL A a pO OPEM ING: ACO x",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 5
}
},
@ -388,22 +454,18 @@
"text": "Fig. 8. SEM/EDX image of stainless steel immersed in 0.5M H SO solution with the presence of inhibitor. 2 4",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 5
}
},
{
"element_id": "f7c9224beff88b5f16795913f8d40072",
"text": "Experimental design, materials and methods",
"element_id": "a80826543c9e0d0e9f6c2108ae3c3f73",
"text": "2. Experimental design, materials and methods",
"type": "Title",
"metadata": {
"page_number": 6
}
},
{
"element_id": "7c3b7c8c2993a59e71e009d051edd727",
"text": "Austenitic stainless steel Type 316 was used in this study with chemical composition reported in [1,2]. The chemicals used were of annular grade. The inhibitor concentrations are in the range of 2, 4, 6, 8 and 10 g [3–5]. The structural formula of egg shell powder is shown in Fig. 9.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
@ -412,6 +474,8 @@
"text": "",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
@ -420,6 +484,8 @@
"text": "Fig. 9. Chemical structure of egg shell powder.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
@ -428,14 +494,18 @@
"text": "2.2. Weight loss method",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
{
"element_id": "027d7539bf229e0a5fd99489c6ebd7fd",
"text": "This physical measurement was carried out in order to provide direct result on how the corrosive environment affects the test sample. The cleaned and weighed specimen was suspended in beakers with the aid of glass hooks and rods with the test solution of ES at different concentration (2, 4, 6, 8 and 10 g). The pre-weighed specimen was retrieved from the test solution after every 24 h, cleaned, dried and reweighed. The difference between the weight at a given time and the initial weight of the specimen was taken as the weight loss which was used to calculate corrosion rate and inhibition efficiency.",
"element_id": "96ac5b6efc55f8db8b7d90a9eb66c65e",
"text": "This physical measurement was carried out in order to provide direct result on how the corrosive environment affects the test sample. The cleaned and weighed specimen was suspended in beakers with the aid of glass hooks and rods with the test solution of ES at different concentration (2, 4, 6, 8 and 10 g). The pre-weighed specimen was retrieved from the test solution after every 24 h, cleaned, dried and reweighed. The difference between the weight at a given time and the initial weight of the specimen was taken as the weight loss which was used to calculate corrosion rate and inhibition efficiency.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
@ -444,22 +514,18 @@
"text": "The corrosion rate (CR) was calculated using Eq. (1)",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
{
"element_id": "b05aa2b4b80cb8c20881dbd0c3af8822",
"text": "where: W is weight loss in mg, A is specimen surface area, T is immersion period in hours and D is the specimen density. From the corrosion rate, the surface coverage (θ) and inhibition efficiencies (IE %) were determined using Eqs. (2) and (3) respectively",
"type": "NarrativeText",
"metadata": {
"page_number": 6
}
},
{
"element_id": "6aa7f759e077aa037614e7f42897f09a",
"text": "2.3. Potentiodynamic polarization method",
"element_id": "51fded1bfb6a8a4c7c8bfd88b5f6e817",
"text": "where: W is weight loss in mg, A is specimen surface area, T is immersion period in hours and D is the specimen density. From the corrosion rate, the surface coverage (θ ) and inhibition efficiencies (IE %) were determined using Eqs. (2) and (3) respectively",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
@ -468,6 +534,8 @@
"text": "The potentiodynamic polarization method was performed on the prepared test samples immersed in 0.5 M H SO solution in the presence and absence of different ES concentrations. A three electrode 2 4 system was used; stainless steel Type 316 plate as working electrode with an exposed area of 1.0 cm2, platinum rod as counter electrode and silver chloride electrode as reference electrode. The electrode was polished, degreased in acetone and thoroughly rinsed with distilled water before the experiment. Current density against applied potential was plotted. The slope of the linear part in anodic and cathodic plots gives anodic and cathodic constants according to the Stern–Geary equation, and the",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 6
}
},
@ -476,14 +544,8 @@
"text": "Acknowledgements",
"type": "Title",
"metadata": {
"page_number": 7
}
},
{
"element_id": "d202816913e482abce90d70d88f202c3",
"text": "Transparency document. Supporting information",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
@ -492,14 +554,308 @@
"text": "References",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d6657099de7fbf009c7de18c9b07bbb3",
"text": "O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, Enhanced corrosion resistance of stainless steel type 316 in sulphuric acid solution using eco-friendly waste product, Results Phys. 9 (2018) 225–230. O. Sanni, A.P.I. Popoola, A. Kolesnikov, Constitutive modeling for prediction of optimal process parameters in corrosion inhibition of austenitic stainless steel (Type 316)/acidic medium, Mater. Res. Express. 5 (10) (2018) 1–15. O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, The inhibitive study of egg shell powder on UNS N08904 austenitic stainless steel corrosion in chloride solution, Def. Technol. 14 (2018) 463–468.",
"type": "NarrativeText",
"element_id": "245843abef9e72e7efac30138a994bf6",
"text": "[",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "9b8d0ee38ce22a5d3a5158f0f9d07c63",
"text": "] O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, Enhanced corrosion resistance of stainless steel type",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "be945a2c885670e97310d1ce55214643",
"text": "in sulphuric acid solution using eco-friendly waste product, Results Phys.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "32ebb1abcc1c601ceb9c4e3c4faba0ca",
"text": "(",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "ba5ec51d07a4ac0e951608704431d59a",
"text": ")",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d4f85d36757c12f0c6dab57721287f32",
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "245843abef9e72e7efac30138a994bf6",
"text": "[",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "ae8fa446f60c67abf074c52a8811735d",
"text": "] O. Sanni, A.P.I. Popoola, A. Kolesnikov, Constitutive modeling for prediction of optimal process parameters in corrosion inhibition of austenitic stainless steel (Type",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d3e62ba74572576eb2c7216f22c998a9",
"text": ")/acidic medium, Mater. Res. Express.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "32ebb1abcc1c601ceb9c4e3c4faba0ca",
"text": "(",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "453543dc0567f05ebf653bee31782e25",
"text": ") (",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "ba5ec51d07a4ac0e951608704431d59a",
"text": ")",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d4f85d36757c12f0c6dab57721287f32",
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "245843abef9e72e7efac30138a994bf6",
"text": "[",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "861f5cbe9d5ceecd1a2d7584b1a3d578",
"text": "] O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, The inhibitive study of egg shell powder on UNS N",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "28d7fffa02c7ef6c9e08b0ef38884ebc",
"text": "austenitic stainless steel corrosion in chloride solution, Def. Technol.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "32ebb1abcc1c601ceb9c4e3c4faba0ca",
"text": "(",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "ba5ec51d07a4ac0e951608704431d59a",
"text": ")",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d4f85d36757c12f0c6dab57721287f32",
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "245843abef9e72e7efac30138a994bf6",
"text": "[",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "a10c3db0e4715ad47ee0c9e03cccc7ca",
"text": "] O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, C.A. Loto, A comparative study of inhibitive effect of waste product on stainless steel corrosion in sodium chloride/sulfuric acid environments, Metallogr. Microstruct. Anal. (",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "ba5ec51d07a4ac0e951608704431d59a",
"text": ")",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d4f85d36757c12f0c6dab57721287f32",
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "24f7ae29478975d5e9bd4eb57c7a0224",
"text": "https://doi.org/",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "d3abf774d65a92eb603ba6230e38d00f",
"text": "/ s",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "3973e022e93220f9212c18d0d0c543ae",
"text": "-",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "3973e022e93220f9212c18d0d0c543ae",
"text": "-",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "3973e022e93220f9212c18d0d0c543ae",
"text": "-",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "245843abef9e72e7efac30138a994bf6",
"text": "[",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
{
"element_id": "dd5bab5ad47eab029cf317b15b97642c",
"text": "] O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, Inhibition of engineering material in sulphuric acid solution using waste product,",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
},
@ -508,6 +864,8 @@
"text": "O. Sanni, A.P.I. Popoola, O.S.I. Fayomi, Inhibition of engineering material in sulphuric acid solution using waste product, Contributed Papers from Materials Science and Technology (MS&T18), 2018. 〈https://doi.org/10.7449/2018/MST_2018_254_261〉.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 7
}
}

306
test_unstructured_ingest/expected-structured-output/biomed-ingest-output-api/75/29/main.PMC6312793.pdf.json
View File

@ -4,6 +4,18 @@
"text": "Contents lists available at ScienceDirect Data in Brief journal homepage: www.elsevier.com/locate/dib",
"type": "FigureCaption",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "0ca3f075fdccf9232449ff461b63ceb9",
"text": "journal homepage: www.elsevier.com/locate/dib",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -12,22 +24,28 @@
"text": "A benchmark dataset for the multiple depot vehicle scheduling problem",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "6171cb8d012b6a4fe0d3d2d559fa8a49",
"text": "Sarang Kulkarni a,b,c,n, Mohan Krishnamoorthy d,e, Abhiram Ranade f, Andreas T. Ernst c, Rahul Patil b",
"element_id": "d3ce4f426ea758d712660638e5db0b32",
"text": "Sarang Kulkarni , Mohan Krishnamoorthy d,e, Abhiram Ranade f, Andreas T. Ernst c, Rahul Patil b",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "1cd8f730884c8b214a75eceab622b553",
"text": "a IITB-Monash Research Academy, IIT Bombay, Powai, Mumbai 400076, India b SJM School of Management, IIT Bombay, Powai, Mumbai 400076, India c School of Mathematical Sciences, Monash University, Clayton, VIC 3800, Australia d Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC 3800, e School of Information Technology and Electrical Engineering, The University of Queensland, QLD",
"element_id": "ebc8429212b65bf771717a75b69e8311",
"text": "a IITB-Monash Research Academy, IIT Bombay, Powai, Mumbai 400076, India b SJM School of Management, IIT Bombay, Powai, Mumbai 400076, India c School of Mathematical Sciences, Monash University, Clayton, VIC 3800, Australia d Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC e School of Information Technology and Electrical Engineering, The University of Queensland, Australia f",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -36,38 +54,58 @@
"text": "of Computer Science and Engineering, IIT Bombay, Powai, Mumbai 400076, India",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "8fd297d1a2817570ee2dfbca314e8039",
"text": "This data article presents a description of a benchmark dataset for the multiple depot vehicle scheduling problem (MDVSP). The MDVSP is to assign vehicles from different depots to timetabled trips to minimize the total cost of empty travel and waiting. The dataset has been developed to evaluate the heuristics of the MDVSP that are presented in “A new formulation and a column generation-based heuristic for the multiple depot vehicle sche- duling problem” (Kulkarni et al., 2018). The dataset contains 60 problem instances of varying size. Researchers can use the dataset to evaluate the future algorithms for the MDVSP and compare the performance with the existing algorithms. The dataset includes a program that can be used to generate new problem instances of the MDVSP.",
"element_id": "b1a854c188d0833c1c573a0462e2a25c",
"text": "This data article presents a description of a benchmark dataset for the multiple depot vehicle scheduling problem (MDVSP). The MDVSP is to assign vehicles from different depots to timetabled trips to minimize the total cost of empty travel and waiting. The dataset has been developed to evaluate the heuristics of the MDVSP that are presented in “A new formulation and a column generation-based heuristic for the multiple depot vehicle sche- duling problem” (Kulkarni et al., 2018). The dataset contains 60 problem instances of varying size. Researchers can use the dataset to evaluate the future algorithms for the MDVSP and compare the performance with the existing algorithms. The dataset includes a program that can be used to generate new problem instances of the MDVSP. & 2018 Published by Elsevier Inc. This is an open access article",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "b16a14378c7e3641edaab4832d548e08",
"text": "(http: ||creativecommons. org/licenses/by- nce-nd/4.0/).",
"element_id": "740791f13b201ca5a9d226b7bcc7791a",
"text": "Published by Elsevier Inc. This is an open access under the CC BY-NC-ND license",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "f7c575292a9d9f0d9d8653435e5d43e1",
"text": "2352-3409/& 2018 Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).",
"element_id": "05176ed2416890f7d4a4655f1e9d87d0",
"text": "(http://creativecommons.org/licenses/by-nc-nd/4.0/).",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "0141e31a627e76fb56d3528957fef193",
"text": "Artificially generated by a Cþ þ program on Intels Xeons CPU E",
"element_id": "30b5af6114bd8cea03b625ca89fa87ae",
"text": "2352-3409/& 2018 Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND (http://creativecommons.org/licenses/by-nc-nd/4.0/).",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "51c33ff4fbc8b914b6ba9a005aafd8eb",
"text": "Vehicle scheduling Tables, text files Artificially generated by a Cþ þ program on Intels Xeons CPU E",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -76,6 +114,8 @@
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -84,6 +124,8 @@
"text": "v",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -92,6 +134,8 @@
"text": "with Linux operating system. Raw Sixty randomly generated instances of the MDVSP with the number of depots in (",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -100,6 +144,8 @@
"text": ",",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -108,6 +154,8 @@
"text": ",",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -116,6 +164,8 @@
"text": ") and the number of trips in (",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -124,6 +174,8 @@
"text": ",",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -132,6 +184,8 @@
"text": ",",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -140,6 +194,8 @@
"text": ",",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -148,22 +204,58 @@
"text": ") Randomly generated instances IITB-Monash Research Academy, IIT Bombay, Powai, Mumbai, India. Data can be downloaded from https://orlib.uqcloud.net/ Kulkarni, S., Krishnamoorthy, M., Ranade, A., Ernst, A.T. and Patil, R.,",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "31d805cba7125109a2f22720089275e6",
"text": "A new formulation and a column generation-based heuristic for the multiple depot vehicle scheduling problem. Transportation",
"element_id": "292e00612ab4cf78a2401d6ae77d9707",
"text": "A new formulation and a column generation-based heuristic for the multiple depot vehicle scheduling problem. Transportation Research Part B: Methodological,",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "f66486b2db409493f9442f275e48a594",
"text": "S., Krishnamoorthy, M., Ranade, A., Ernst, A.T. and Patil, R., A new formulation and a column generation-based heuristic for multiple depot vehicle scheduling problem. Transportation Part B: Methodological, 118, pp. 457–487 [3].",
"type": "NarrativeText",
"element_id": "803dac27c4823a821bc305f70dfa7a04",
"text": ", pp.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "d4f85d36757c12f0c6dab57721287f32",
"text": "–",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "245843abef9e72e7efac30138a994bf6",
"text": "[",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "a00ad12fa538b6cae76f5413d3a14e45",
"text": "].",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -172,86 +264,58 @@
"text": "Value of the data",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "a0ec1ff22b659610fcf5e590b34f6716",
"text": "(cid:",
"element_id": "9bf39412d343706db6a940993c139203",
"text": "The dataset contains",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "c450824d50e14047feb63a3e823f4e79",
"text": ") The dataset contains",
"element_id": "92ab3a2ee9821fa27cc768e07733d529",
"text": "different problem instances of the MDVSP that can be used to evaluate performance of the algorithms for the MDVSP. The data provide all the information that is required to model the MDVSP by using the mathematical formulations. All the problem instances are available for use without any restrictions. The benchmark solutions and solution time for the problem instances are presented in [",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "71f5d9d02f796abf77f6c8cefccfbbc6",
"text": "different problem instances of the MDVSP that can be used to evaluate performance of the algorithms for the MDVSP. (cid:",
"element_id": "618c071d9085dc44b5ccad73b6891cd5",
"text": "] and be used for the comparison.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "ff9a3de64cbe3f036663277a1244b4f1",
"text": ") The data provide all the information that is required to model the MDVSP by using the mathematical formulations. (cid:",
"type": "ListItem",
"element_id": "c2b2b778d53cc9a1cb4dc340476bc5aa",
"text": "1. Data",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "e0d4a2eb6e524ab6a940a80cac00ddc5",
"text": ") All the problem instances are available for use without any restrictions. (cid:",
"type": "ListItem",
"metadata": {
"page_number": 2
}
},
{
"element_id": "2c1b57c4582a3df9d4356f76304eddc8",
"text": ") The benchmark solutions and solution time for the problem instances are presented in [",
"type": "ListItem",
"metadata": {
"page_number": 2
}
},
{
"element_id": "cc161a19fc428fc287dcf14f1654e0cb",
"text": "] and be used for the comparison. (cid:",
"type": "ListItem",
"metadata": {
"page_number": 2
}
},
{
"element_id": "72aa6ba1397a323ae5bece0093a9a3a4",
"text": ") The dataset includes a program that can generate similar problem instances of different sizes.",
"type": "ListItem",
"metadata": {
"page_number": 2
}
},
{
"element_id": "2d6c133ed11dddace9e2df5f4cd678c5",
"text": "dataset includes a program that can generate similar problem instances of different sizes.",
"type": "NarrativeText",
"metadata": {
"page_number": 2
}
},
{
"element_id": "d6a9448e0184c8bd5e12eb3a97e140c7",
"text": "The dataset contains 60 different problem instances of the multiple depot vehicle scheduling pro- blem (MDVSP). Each problem instance is provided in a separate file. Each file is named as ‘RN-m-n-k.dat’, where ‘m’, ‘n’, and ‘k’ denote the number of depots, the number of trips, and the instance number for the size, ‘ðm;nÞ’, respectively. For example, the problem instance, ‘RN-8–1500-01.dat’, is the first problem instance with 8 depots and 1500 trips. For the number of depots, m, we used three values, 8,12, and 16. The four values for the number of trips, n, are 1500, 2000, 2500, and 3000. For each size, ðm;nÞ, five instances are provided. The dataset can be downloaded from https://orlib.uqcloud.net. For each problem instance, the following information is provided:",
"element_id": "1cf83f090d4cf11db6708eb75235a23a",
"text": "The dataset contains 60 different problem instances of the multiple depot vehicle scheduling pro- blem (MDVSP). Each problem instance is provided in a separate file. Each file is named as ‘RN-m-n-k.dat’, where ‘m’, ‘n’, and ‘k’ denote the number of depots, the number of trips, and the instance number for the size, ‘ðm;nÞ’, respectively. For example, the problem instance, ‘RN-8–1500-01.dat’, is the first problem instance with 8 depots and 1500 trips. For the number of depots, m, we used three values, 8,12, and 16. The four values for the number of trips, n, are 1500, 2000, 2500, and 3000. For each size, ðm;nÞ, five instances are provided. The dataset can be downloaded from https://orlib.uqcloud.net. For each problem instance, the following information is provided:",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -260,6 +324,8 @@
"text": "The number of depots ðmÞ, The number of trips ðnÞ, The number of locations ðlÞ, The number of vehicles at each depot, For each trip",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -268,22 +334,28 @@
"text": ";",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "a39bfd8cfef6541b044847975896a2c6",
"text": ";…;n, a start time, ts, an end time, te, a start location, ls, and an end i i i and",
"element_id": "f90e295ef04a2cfe1cf4d20d93aa8cea",
"text": ";…;n, a start time, ts, an end time, te, a start location, ls , and an end location, i i i and",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "81cf45127cb8d3e1c01ffca5e41ead4b",
"text": "(cid:2) The travel time, , between any two locations i;jA1;…;l. ij",
"element_id": "26bc8b937250fbd91a2ff2f75fad7bb4",
"text": "The travel time, , between any two locations i;jA1;…;l. ij",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
@ -292,38 +364,38 @@
"text": "All times are in minutes and integers. The planning duration is from 5 a.m. to around midnight. Each instance has two classes of trips, short trips and long trips, with 40% short trips and 60% long trips. The duration of a short trip is less than a total of 45 min and the travel time between the start",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 2
}
},
{
"element_id": "e1e2a818fd38b9f4952535d26fb659a0",
"text": "and end location of the trip. A long trip is about 3–5 h in duration and has the same start and end location. For all instances, mrl and the locations 1;…;m correspond to depots, while the remaining locations only appear as trip start and end locations.",
"element_id": "04d6da7763330fba2e000f1550d624b4",
"text": "A trip j can be covered after trip i by the same vehicle, if . If , the vehicle must j i lels i j i j travel empty from le to ls , otherwise, the vehicle may require waiting at le for the duration of ðts(cid:3)teÞ. i j i j i A schedule is given by the sequence in which a vehicle can cover the trips. The MDVSP is to determine the minimum number of schedules to cover all trips that minimizes total time in waiting and empty travel. The following requirements must be satisfied:",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "ce2e201f29b7016ecce46d1d693ef7b4",
"text": "j i lels i j i j travel empty from le to ls, otherwise, the vehicle may require waiting at le for the duration of i j i j i A schedule is given by the sequence in which a vehicle can cover the trips. The MDVSP is to the minimum number of schedules to cover all trips that minimizes total time in waiting and travel. The following requirements must be satisfied:",
"element_id": "4b7e68562517c3a2f4736cf12e1ef395",
"text": "For each instance size ðm;nÞ, Table 1 provides the average of the number of locations, the number of times, the number of vehicles, and the number of possible empty travels, over five instances. The number of locations includes m distinct locations for depots and the number of locations at which various trips start or end. The number of times includes the start and the end time of the planning horizon and the start/end times for the trips. The number of vehicles is the total number of vehicles from all the depots. The number of possible empty travels is the number of possible connections between trips that require a vehicle travelling empty between two consecutive trips in a schedule.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "cd9bf519d24539b268f95eac88c85d58",
"text": "For each instance size ðm;nÞ, Table 1 provides the average of the number of locations, the number of times, the number of vehicles, and the number of possible empty travels, over five instances. The number of locations includes m distinct locations for depots and the number of locations at which various trips start or end. The number of times includes the start and the end time of the planning horizon and the start/end times for the trips. The number of vehicles is the total number of vehicles from all the depots. The number of possible empty travels is the number of possible connections between trips that require a vehicle travelling empty between two consecutive trips in a schedule.",
"type": "NarrativeText",
"metadata": {
"page_number": 3
}
},
{
"element_id": "15ccc43b8b50ed7b5fc5ea342405a929",
"text": "The description of the file for each problem instance is presented in Table 2. The first line in the file provides the number of depots ðmÞ, the number of trips, ðnÞ, and the number of locations ðlÞ, in the problem instance. The next n lines present the information for n trips. Each line corresponds to a trip, iAf1;…;ng, and provides the start location, the start time, the end location, and the end time of trip i. (cid:1) (cid:3)",
"element_id": "1723544d316dcd5a701b0f160dc965c8",
"text": "The description of the file for each problem instance is presented in Table 2. The first line in the file provides the number of depots ðmÞ, the number of trips, ðnÞ, and the number of locations ðlÞ, in the problem instance. The next n lines present the information for n trips. Each line corresponds to a trip, iAf1;…;ng, and provides the start location, the start time, the end location, and the end time of trip i. n,a the The next l lines present the travel times between any two locations, i;jA 1;…;l . The dataset also includes a program ‘GenerateInstance.cpp’ that can be used to generate new instances. The program takes three inputs, the number of depots ðmÞ, the number of trips ðnÞ, and the",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
@ -332,22 +404,28 @@
"text": "The dataset also includes a program ‘GenerateInstance.cpp’ that can be used to generate new instances. The program takes three inputs, the number of depots ðmÞ, the number of trips ðnÞ, and the number of instances for each size ðm;nÞ.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "56c0242fd0b5157ca054988ab468e5b1",
"text": "Average number of locations, times, vehicles and empty travels for each instance size.",
"element_id": "7f59d58d0387d28ff45422e8dc6d7e3c",
"text": "Average number of locations, times, vehicles and empty travels for each instance",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
{
"element_id": "d64be61ce583c012d79a10c894d35806",
"text": "Instance size (m, n) Average number of Locations Times Vehicles Possible empty travels (8, 1500) 568.40 975.20 652.20 668,279.40 (8, 2000) 672.80 1048.00 857.20 1,195,844.80 (8, 2500) 923.40 1078.00 1082.40 1,866,175.20 (8, 3000) 977.00 1113.20 1272.80 2,705,617.00 (12, 1500) 566.00 994.00 642.00 674,191.00 (12, 2000) 732.60 1040.60 861.20 1,199,659.80 (12, 2500) 875.00 1081.00 1096.00 1,878,745.20 (12, 3000) 1119.60 1107.40 1286.20 2,711,180.40 (16, 1500) 581.80 985.40 667.80 673,585.80 (16, 2000) 778.00 1040.60 872.40 1,200,560.80 (16, 2500) 879.00 1083.20 1076.40 1,879,387.00 (16, 3000) 1087.20 1101.60 1284.60 2,684,983.60",
"type": "UncategorizedText",
"type": "Table",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 3
}
},
@ -356,14 +434,28 @@
"text": "Table 2",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
{
"element_id": "fec9cdb50e095b07d7653f500e145481",
"text": "Description of file format for each problem instance.",
"element_id": "3e7e3e4379cf8816544d3850e7bc2e28",
"text": "Description of file format for each problem instance.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
{
"element_id": "444f48f6d4f0ee6d3a04b7bf76218980",
"text": "Number of Number of columns in Description lines each line",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -372,6 +464,8 @@
"text": "The number of depots, the number of trips, and the number of locations. The number of vehicles r at each depot d. d One line for each trip, i¼",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -380,6 +474,8 @@
"text": ";",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -388,6 +484,8 @@
"text": ";…;n. Each line provides the start location ls, the start i time ts, the end location le and the end time te for the corresponding trip. i i i Each element, δ ; where i;",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -396,6 +494,8 @@
"text": ";",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -404,6 +504,8 @@
"text": ";…;l, refers to the travel time between location i and ij location j.",
"type": "ListItem",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -412,14 +514,18 @@
"text": "2. Experimental design, materials, and methods",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
{
"element_id": "cfd640766bf0c2b995b2f4dab227edd2",
"text": "The procedure presented by Carpaneto et al. in [1] is used to generate the problem instances. The same procedure has been used by Pepin et al. in [4] to generate the benchmark dataset of the MDVSP. A detailed description of the procedure is presented in [3].",
"element_id": "d7a335a83b8b7caabf5c2a1d748bd06a",
"text": "The procedure presented by Carpaneto et al. in [1] is used to generate the problem instances. same procedure has been used by Pepin et al. in [4] to generate the benchmark dataset of the A detailed description of the procedure is presented in [3].",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -428,14 +534,18 @@
"text": "Our dataset provides start/end location and time of trips as well as the travel time between any two locations. The location and time information is required to model the MDVSP on a time-space network. The feasible connections and the cost of connections between the trips can be obtained as discussed in [3]. Thus, the dataset has all the information that is required to model the MDVSP on the time-space network (see [2]) as well as the connection-network (see [5]). The benchmark solutions for all the problem instances are presented in [3].",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
{
"element_id": "d202816913e482abce90d70d88f202c3",
"text": "Transparency document. Supporting information",
"type": "Title",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
@ -444,14 +554,18 @@
"text": "References",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
},
{
"element_id": "779c8db2c33a770fc051ffa089c1ea73",
"text": "[1] G. Carpaneto, M. Dell'Amico, M. Fischetti, P. Toth, A branch and bound algorithm for the multiple depot vehicle scheduling problem, Networks 19 (5) (1989) 531–548. [2] N. Kliewer, T. Mellouli, L. Suhl, A time–space network based exact optimization model for multi-depot bus scheduling, Eur. J. Oper. Res. 175 (3) (2006) 1616–1627. [3] S. Kulkarni, M. Krishnamoorthy, A. Ranade, A.T. Ernst, R. Patil, A new formulation and a column generation-based heuristic for the multiple depot vehicle scheduling problem, Transp. Res. Part B Methodol. 118 (2018) 457–487. [4] A.S. Pepin, G. Desaulniers, A. Hertz, D. Huisman, A comparison of five heuristics for the multiple depot vehicle scheduling problem, J. Sched. 12 (1) (2009) 17. [5] C.C. Ribeiro, F. Soumis, A column generation approach to the multiple-depot vehicle scheduling problem, Oper. Res. 42 (1) (1994) 41–52.",
"element_id": "af77eddb4e5b699e2125b58884984195",
"text": "[1] G. Carpaneto, M. Dell'Amico, M. Fischetti, P. Toth, A branch and bound algorithm for the multiple depot vehicle scheduling problem, Networks 19 (5) (1989) 531–548. [2] N. Kliewer, T. Mellouli, L. Suhl, A time–space network based exact optimization model for multi-depot bus scheduling, Eur. J. Oper. Res. 175 (3) (2006) 1616–1627. [3] S. Kulkarni, M. Krishnamoorthy, A. Ranade, A.T. Ernst, R. Patil, A new formulation and a column generation-based heuristic for the multiple depot vehicle scheduling problem, Transp. Res. Part B Methodol. 118 (2018) 457–487. [4] A.S. Pepin, G. Desaulniers, A. Hertz, D. Huisman, A comparison of five heuristics for the multiple depot vehicle scheduling problem, J. Sched. 12 (1) (2009) 17. [5] C.C. Ribeiro, F. Soumis, A column generation approach to the multiple-depot vehicle scheduling problem, Oper. Res. 42 (1) (1994) 41–52.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 4
}
}

102
test_unstructured_ingest/expected-structured-output/biomed-ingest-output-path/07/07/sbaa031.073.PMC7234218.pdf.json
View File

@ -1,17 +1,21 @@
[
{
"element_id": "212ffda01df6b088ef8492dc27e5e461",
"text": "40 mg/day=3.6%, p<0.05; 80 mg/day=4.9%, p<0.01; 120 PM dosing group: 20 mg/day=-0.4%, ns; 40",
"type": "NarrativeText",
"metadata": {
"page_number": 1
}
},
{
"element_id": "e77987c7b17439bcfe8150c849de15a9",
"text": "Discussion: Our data confirm previous findings on reduced slow wave density in FEP, and expand them to acute subjects, before any treatment is prescribed. This is in line with available data on diffuse abnormalities of cortico-cortical and cortico-thalamic networks in these patients. Interestingly, our data also offer preliminary evidence that this deficit is specific for SCZ, as it appears to differentiate patients who developed SCZ from those with other diagnoses at follow-up. Given the traveling properties of slow waves, future research should establish their potential as markers of connectivity in SCZ.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "212ffda01df6b088ef8492dc27e5e461",
"text": "40 mg/day=3.6%, p<0.05; 80 mg/day=4.9%, p<0.01; 120 PM dosing group: 20 mg/day=-0.4%, ns; 40",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -20,22 +24,8 @@
"text": "p<0.001, PM dosing group: 20 mg/day=-0.4%, ns; 40 mg/day=2.8%, p<0.05: 80 mg/day=0.2%, ns; 160 mg/day=5.8%, p<0.05). There was no clear dose-dependent trend associated with nausea and RD was similar between AM and PM dosing group (AM dosing group: 20 mg/ day=0.2% ns; 40 mg/day=3.8%, p<0.05; 80 mg/day=3.8%, ns; 120 mg/ day=6.6%, ns, PM dosing group: 20 mg/day=-1.6%, ns; 40 mg/day=-1.7%, ns; 80 mg/day=5.5%, p<0.01; 160 mg/day=2.8%, ns). Discussion: The risk of adverse events in the treatment of schizophrenia with lurasidone can vary depending on the timing of administration. In particular, for akathisia and somnolence, the incidence risks were reduced when lurasidone was administered in PM. Unlike with AM administration, the dose-dependence in the risks of these adverse events were not observed in lurasidone PM administration. The timing of lurasidone administration could be considered in effort to minimize potential adverse events.",
"type": "NarrativeText",
"metadata": {
"page_number": 1
}
},
{
"element_id": "e2f659c61ce09e9fff495ceea8e6d949",
"text": "There was no clear dose-dependent trend associated with nausea and RD was similar between AM and PM dosing group (AM dosing group: 20 mg/ day=0.2% ns; 40 mg/day=3.8%, p<0.05; 80 mg/day=3.8%, ns; 120 mg/ day=6.6%, ns, PM dosing group: 20 mg/day=-1.6%, ns; 40 mg/day=-1.7%, ns; 80 mg/day=5.5%, p<0.01; 160 mg/day=2.8%, ns).",
"type": "NarrativeText",
"metadata": {
"page_number": 1
}
},
{
"element_id": "9a9ab575daf99c2971dccf9ab81b7afe",
"text": "Discussion: The risk of adverse events in the treatment of schizophrenia with lurasidone can vary depending on the timing of administration. In particular, for akathisia and somnolence, the incidence risks were reduced when lurasidone was administered in PM. Unlike with AM administration, the dose-dependence in the risks of these adverse events were not observed in lurasidone PM administration. The timing of lurasidone administration could be considered in effort to",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -44,14 +34,18 @@
"text": "S7. INVESTIGATING THE LINK BETWEEN THE PERIPHERAL ENDOCANNABINOID SYSTEM AND CENTRAL GLUTAMATERGIC NEUROTRANSMISSION IN EARLY PSYCHOSIS: A 7T-MRS STUDY",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "5ce0f6dc16582eaf81312c412e99ebb9",
"text": "Amedeo Minichino*1, Beata Godlewska1, Philip Cowen1, Philip Burnet1, Belinda Lennox1 1University of Oxford",
"element_id": "f840a64edde30227ef811444e3d98073",
"text": "Amedeo Minichino*1, Beata Godlewska1, Philip Cowen1, Philip Burnet1, Belinda Lennox1",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -60,6 +54,8 @@
"text": "S6. SLEEP ENDOPHENOTYPES OF SCHIZOPHRENIA: A HIGH-DENSITY EEG STUDY IN DRUG-NAÏVE, FIRST EPISODE PSYCHOSIS PATIENTS",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -68,6 +64,8 @@
"text": "Background: Meta-analytic evidence showed increased levels of periph- eral endocannabinoid metabolites in psychotic illness. Alterations in the endocannabinoid system are believed to compromise glutamate and do- pamine transmission, which play a central role in pathophysiological models of psychosis. I will present preliminary data from an ongoing high-field proton magnetic resonance spectroscopy (MRS) study aimed at investigating the association between peripheral levels of endocannabinoid system metabolites and central glutamate metabolism in individuals at their",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -76,6 +74,8 @@
"text": "eral endocannabinoid metabolites in psychotic illness. Alterations in the endocannabinoid system are believed to compromise glutamate and do- pamine transmission, which play a central role in pathophysiological models of psychosis. I will present preliminary data from an ongoing high-field proton magnetic resonance spectroscopy (MRS) study aimed at investigating the association between peripheral levels of endocannabinoid system metabolites and central glutamate metabolism in individuals at their first non-affective psychotic episode (NA-FEP) and healthy controls. Methods: We expect to recruit 17 NA-FEP and 20 healthy controls by January 2020. Currently, we recruited 12 NA-FEP and 18 healthy controls from two different research facilities (Imperial College London and University of Oxford) as part of a cross-sectional study. Participants un- derwent MRS scanning at 7-T with voxels placed in right dorsolateral prefrontal cortex (right-DLPFC), anterior cingulate cortex (ACC), and oc- cipital cortex. Neuro-metabolites will be calculated using the unsuppressed water signal as reference. Endocannabinoid metabolites were quantified from serum samples, collected during the same imaging session. Results: Analyses are ongoing. Based on previous evidence, expected findings are: (i) reduced glutamate levels in the ACC and right-DLPFC of NA-FEP compared to controls; (ii) increased peripheral endocannabinoid metabolites in NA-FEP compared to controls; and (iii) inverse association between peripheral endocannabinoid metabolites and glutamate levels in ACC and right-DLPFC in NA-FEP Discussion: This study will help clarifying the contribution of peripheral endocannabinoid system to central brain mechanisms of key relevance for psychotic illness. It will also add further evidence on the limited literature on high-resolution characterisation of brain metabolites in early psychosis. Strengths of the study include: (i) use of high-field MRS, which allows the estimation of glutamate-related compounds at higher precision than at lower field strength; (ii) reduced heterogeneity of the clinical sample (only male and NA-FEP). Limitations: small sample size and cross-sectional design.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -84,22 +84,28 @@
"text": "Anna Castelnovo1, Cecilia Casetta2, Francesco Donati3, Renata del Giudice3, Caroline Zangani3, Simone Sarasso3,",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "948648391aef568cca125eb01b3c3a0e",
"text": "1Faculty of Biomedical Sciences, Università della Svizzera Italiana, Switzerland; 2Institute of Psychiatry, Psychology and Neuroscience, King’s College London, England; 3Università degli Studi di Milano,",
"element_id": "7bd18c510f2f36052d646353186ec9b9",
"text": "1Faculty of Biomedical Sciences, Università della Svizzera Italiana, Switzerland; 2Institute of Psychiatry, Psychology and Neuroscience, King’s College London, England; 3Università degli Studi di Milano, Italy",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "7131a6e69b1ce9e87e8057dcd9b30fb4",
"text": "We expect to recruit 17 NA-FEP and 20 healthy controls by 2020. Currently, we recruited 12 NA-FEP and 18 healthy controls two different research facilities (Imperial College London and of Oxford) as part of a cross-sectional study. Participants un- MRS scanning at 7-T with voxels placed in right dorsolateral cortex (right-DLPFC), anterior cingulate cortex (ACC), and oc- cortex. Neuro-metabolites will be calculated using the unsuppressed signal as reference. Endocannabinoid metabolites were quantified serum samples, collected during the same imaging session.",
"element_id": "8f3a9a89266b324f14a3581b118075ee",
"text": "Methods: We expect to recruit 17 NA-FEP and 20 healthy controls by January 2020. Currently, we recruited 12 NA-FEP and 18 healthy controls from two different research facilities (Imperial College London and University of Oxford) as part of a cross-sectional study. Participants un- derwent MRS scanning at 7-T with voxels placed in right dorsolateral prefrontal cortex (right-DLPFC), anterior cingulate cortex (ACC), and oc- cipital cortex. Neuro-metabolites will be calculated using the unsuppressed water signal as reference. Endocannabinoid metabolites were quantified from serum samples, collected during the same imaging session. Results: Analyses are ongoing. Based on previous evidence, expected",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -108,14 +114,8 @@
"text": "Background: Slow waves, the hallmark of the deep nonrapid eye move- ment sleep electroencephalogram (EEG), are critical for restorative sleep and brain plasticity. They arise from the synchronous depolarization and hyperpolarization of millions of cortical neurons and their proper gen- eration and propagation relies upon the integrity of widespread cortico- thalamic networks. Slow wave abnormalities have been reported in patient with Schizophrenia, although with partially contradictory results, probably related to antipsychotic and sedative medications. Recently, their presence and delineation, have been convincingly shown in first-episode psychosis patients (FEP). However, clear evidence of this biomarker at the onset of the disease, prior to any psychopharmacological intervention, remains limited. Moreover, no attempt has been made to elucidate the prognostic meaning of this finding.",
"type": "NarrativeText",
"metadata": {
"page_number": 1
}
},
{
"element_id": "1d4fddbc44df78bdcfa046a23c06edad",
"text": "eration and propagation relies upon the integrity of widespread cortico- thalamic networks. Slow wave abnormalities have been reported in patient with Schizophrenia, although with partially contradictory results, probably related to antipsychotic and sedative medications. Recently, their presence and delineation, have been convincingly shown in first-episode psychosis patients (FEP). However, clear evidence of this biomarker at the onset of the disease, prior to any psychopharmacological intervention, remains limited. Moreover, no attempt has been made to elucidate the prognostic meaning of this finding. Methods: We collected whole night sleep high–density electroencephalog- raphy recordings (64-channel BrainAmp, Brain Products GmbH, Gilching, Germany) in 20 drug-naive FEP patients and 20 healthy control subjects (HC). Several clinical psychometric scales as well as neurocognitive tests were administered to all subjects in order to better define psychopatholog- ical status and vulnerability. EEG slow wave activity (SWA, spectral power between 1 and 4 Hz) and several slow wave parameters were computed at each electrode location, including density and amplitude, at each electrode location. Along with a group analysis between FEP and HC, a subgroup analysis was also computed between patients who showed a progression of symptoms to full-blown Schizophrenia (SCZ, n = 10) over the next 12-month follow-up and those who did not (OTH, n = 10). Results: Sleep macro-architecture was globally preserved in FEP patients. SWA (1–4 Hz) was lower in FEP compared to HC but this difference didn’t reach statistical significance. Slow wave density was decreased in FEP compared to HC, with a significance that survived multiple comparison correction over a large fronto-central cluster. Mean amplitude was pre- served. At the subgroup analysis, these results were largely driven by the",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -124,22 +124,28 @@
"text": "Results: Analyses are ongoing. Based on previous evidence, expected findings are: (i) reduced glutamate levels in the ACC and right-DLPFC of NA-FEP compared to controls; (ii) increased peripheral endocannabinoid metabolites in NA-FEP compared to controls; and (iii) inverse association between peripheral endocannabinoid metabolites and glutamate levels in ACC and right-DLPFC in NA-FEP",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "65b1fe28ae05d86009c6510c0c74678f",
"text": "We collected whole night sleep high–density electroencephalog- recordings (64-channel BrainAmp, Brain Products GmbH, Gilching, in 20 drug-naive FEP patients and 20 healthy control subjects Several clinical psychometric scales as well as neurocognitive tests administered to all subjects in order to better define psychopatholog- status and vulnerability. EEG slow wave activity (SWA, spectral power 1 and 4 Hz) and several slow wave parameters were computed at electrode location, including density and amplitude, at each electrode Along with a group analysis between FEP and HC, a subgroup was also computed between patients who showed a progression symptoms to full-blown Schizophrenia (SCZ, n = 10) over the next follow-up and those who did not (OTH, n = 10).",
"element_id": "80c41b4abd6c3d2ad145cc4d726be8ec",
"text": "raphy recordings (64-channel BrainAmp, Brain Products GmbH, Gilching, Germany) in 20 drug-naive FEP patients and 20 healthy control subjects (HC). Several clinical psychometric scales as well as neurocognitive tests were administered to all subjects in order to better define psychopatholog- ical status and vulnerability. EEG slow wave activity (SWA, spectral power between 1 and 4 Hz) and several slow wave parameters were computed at each electrode location, including density and amplitude, at each electrode location. Along with a group analysis between FEP and HC, a subgroup analysis was also computed between patients who showed a progression of symptoms to full-blown Schizophrenia (SCZ, n = 10) over the next 12-month follow-up and those who did not (OTH, n = 10). Results: Sleep macro-architecture was globally preserved in FEP patients. SWA (1–4 Hz) was lower in FEP compared to HC but this difference didn’t",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "6d5ea0bda7d2f1230a685467bd04226d",
"text": "Discussion: This study will help clarifying the contribution of peripheral endocannabinoid system to central brain mechanisms of key relevance for psychotic illness. It will also add further evidence on the limited literature on high-resolution characterisation of brain metabolites in early psychosis. Strengths of the study include: (i) use of high-field MRS, which allows the estimation of glutamate-related compounds at higher precision than at lower field strength; (ii) reduced heterogeneity of the clinical sample (only male and NA-FEP). Limitations: small sample size and cross-sectional design.",
"element_id": "cd6ce42dd231c70217aa183b1df8fc63",
"text": "Results: Sleep macro-architecture was globally preserved in FEP patients. SWA (1–4 Hz) was lower in FEP compared to HC but this difference didn’t reach statistical significance. Slow wave density was decreased in FEP compared to HC, with a significance that survived multiple comparison correction over a large fronto-central cluster. Mean amplitude was pre- served. At the subgroup analysis, these results were largely driven by the subgroup of patients with a confirmed diagnosis of SCZ at a 12-month fol- low-up. Indeed, no difference could be found between OTH and HC, while a strong significance was still evident between SCZ and HC.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -148,14 +154,8 @@
"text": "S8. GRIN1 PROMOTER METHYLATION CHANGES IN BLOOD OF EARLY-ONSET PSYCHOTIC PATIENTS AND UNAFFECTED SIBLINGS WITH CHILDHOOD TRAUMA",
"type": "Title",
"metadata": {
"page_number": 1
}
},
{
"element_id": "859a428fe717e3dedcb56d828a366cba",
"text": "SWA (1–4 Hz) was lower in FEP compared to HC but this difference didn’t reach statistical significance. Slow wave density was decreased in FEP compared to HC, with a significance that survived multiple comparison correction over a large fronto-central cluster. Mean amplitude was pre- served. At the subgroup analysis, these results were largely driven by the subgroup of patients with a confirmed diagnosis of SCZ at a 12-month fol- low-up. Indeed, no difference could be found between OTH and HC, while a strong significance was still evident between SCZ and HC.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
@ -164,6 +164,8 @@
"text": "Camila Loureiro*1, Corsi-Zuelli Fabiana1, Fachim Helene Aparecida1, Shuhama Rosana1, Menezes Paulo Rossi1, Dalton Caroline F2,",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
}

1842
test_unstructured_ingest/expected-structured-output/pdf-fast-reprocess/biomed-api/65/11/main.PMC6312790.pdf.json Normal file
View File

File diff suppressed because it is too large Load Diff

1072
test_unstructured_ingest/expected-structured-output/pdf-fast-reprocess/biomed-api/75/29/main.PMC6312793.pdf.json Normal file
View File

File diff suppressed because it is too large Load Diff

142
test_unstructured_ingest/expected-structured-output/pdf-fast-reprocess/biomed-path/07/07/sbaa031.073.PMC7234218.pdf.json Normal file
View File

@ -0,0 +1,142 @@
[
{
"element_id": "055b9fd1463ee2c4481b4eb9e20d4b0f",
"text": "S32",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "b8b976f4707d2af116239c70acf8f2be",
"text": "Poster Session I",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "f7573da2765829e5fcbc8eed02057106",
"text": "ns; 40 mg/day=3.6%, p<0.05; 80 mg/day=4.9%, p<0.01; 120 mg/day=9.3%, p<0.001, PM dosing group: 20 mg/day=-0.4%, ns; 40 mg/day=2.8%, p<0.05: 80 mg/day=0.2%, ns; 160 mg/day=5.8%, p<0.05). There was no clear dose-dependent trend associated with nausea and RD was similar between AM and PM dosing group (AM dosing group: 20 mg/ day=0.2% ns; 40 mg/day=3.8%, p<0.05; 80 mg/day=3.8%, ns; 120 mg/ day=6.6%, ns, PM dosing group: 20 mg/day=-1.6%, ns; 40 mg/day=-1.7%, ns; 80 mg/day=5.5%, p<0.01; 160 mg/day=2.8%, ns). Discussion: The risk of adverse events in the treatment of schizophrenia with lurasidone can vary depending on the timing of administration. In particular, for akathisia and somnolence, the incidence risks were reduced when lurasidone was administered in PM. Unlike with AM administration, the dose-dependence in the risks of these adverse events were not observed in lurasidone PM administration. The timing of lurasidone administration could be considered in effort to minimize potential adverse events.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "e77987c7b17439bcfe8150c849de15a9",
"text": "Discussion: Our data confirm previous findings on reduced slow wave density in FEP, and expand them to acute subjects, before any treatment is prescribed. This is in line with available data on diffuse abnormalities of cortico-cortical and cortico-thalamic networks in these patients. Interestingly, our data also offer preliminary evidence that this deficit is specific for SCZ, as it appears to differentiate patients who developed SCZ from those with other diagnoses at follow-up. Given the traveling properties of slow waves, future research should establish their potential as markers of connectivity in SCZ.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "15ef5407945d4d6b7863b5afaeb5ccb7",
"text": "S7. INVESTIGATING THE LINK BETWEEN THE PERIPHERAL ENDOCANNABINOID SYSTEM AND CENTRAL GLUTAMATERGIC NEUROTRANSMISSION IN EARLY PSYCHOSIS: A 7T-MRS STUDY",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "5ce0f6dc16582eaf81312c412e99ebb9",
"text": "Amedeo Minichino*1, Beata Godlewska1, Philip Cowen1, Philip Burnet1, Belinda Lennox1 1University of Oxford",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "87729f38cab913c4c23019736f8609f0",
"text": "S6. SLEEP ENDOPHENOTYPES OF SCHIZOPHRENIA: A HIGH-DENSITY EEG STUDY IN DRUG-NAÏVE, FIRST EPISODE PSYCHOSIS PATIENTS",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "9e7cc386b1093b082bccf936861747aa",
"text": "Background: Meta-analytic evidence showed increased levels of periph- eral endocannabinoid metabolites in psychotic illness. Alterations in the endocannabinoid system are believed to compromise glutamate and do- pamine transmission, which play a central role in pathophysiological models of psychosis. I will present preliminary data from an ongoing high-field proton magnetic resonance spectroscopy (MRS) study aimed at investigating the association between peripheral levels of endocannabinoid system metabolites and central glutamate metabolism in individuals at their first non-affective psychotic episode (NA-FEP) and healthy controls. Methods: We expect to recruit 17 NA-FEP and 20 healthy controls by January 2020. Currently, we recruited 12 NA-FEP and 18 healthy controls from two different research facilities (Imperial College London and University of Oxford) as part of a cross-sectional study. Participants un- derwent MRS scanning at 7-T with voxels placed in right dorsolateral prefrontal cortex (right-DLPFC), anterior cingulate cortex (ACC), and oc- cipital cortex. Neuro-metabolites will be calculated using the unsuppressed water signal as reference. Endocannabinoid metabolites were quantified from serum samples, collected during the same imaging session. Results: Analyses are ongoing. Based on previous evidence, expected findings are: (i) reduced glutamate levels in the ACC and right-DLPFC of NA-FEP compared to controls; (ii) increased peripheral endocannabinoid metabolites in NA-FEP compared to controls; and (iii) inverse association between peripheral endocannabinoid metabolites and glutamate levels in ACC and right-DLPFC in NA-FEP Discussion: This study will help clarifying the contribution of peripheral endocannabinoid system to central brain mechanisms of key relevance for psychotic illness. It will also add further evidence on the limited literature on high-resolution characterisation of brain metabolites in early psychosis. Strengths of the study include: (i) use of high-field MRS, which allows the estimation of glutamate-related compounds at higher precision than at lower field strength; (ii) reduced heterogeneity of the clinical sample (only male and NA-FEP). Limitations: small sample size and cross-sectional design.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "e97f1cf1c49f397732e68cf1efb2355e",
"text": "Anna Castelnovo1, Cecilia Casetta2, Francesco Donati3, Renata del Giudice3, Caroline Zangani3, Simone Sarasso3, Armando D’Agostino*3 1Faculty of Biomedical Sciences, Università della Svizzera Italiana, Switzerland; 2Institute of Psychiatry, Psychology and Neuroscience, King’s College London, England; 3Università degli Studi di Milano, Italy",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "1252f8d8921acac5f706e4402e504a75",
"text": "Background: Slow waves, the hallmark of the deep nonrapid eye move- ment sleep electroencephalogram (EEG), are critical for restorative sleep and brain plasticity. They arise from the synchronous depolarization and hyperpolarization of millions of cortical neurons and their proper gen- eration and propagation relies upon the integrity of widespread cortico- thalamic networks. Slow wave abnormalities have been reported in patient with Schizophrenia, although with partially contradictory results, probably related to antipsychotic and sedative medications. Recently, their presence and delineation, have been convincingly shown in first-episode psychosis patients (FEP). However, clear evidence of this biomarker at the onset of the disease, prior to any psychopharmacological intervention, remains limited. Moreover, no attempt has been made to elucidate the prognostic meaning of this finding. Methods: We collected whole night sleep high–density electroencephalog- raphy recordings (64-channel BrainAmp, Brain Products GmbH, Gilching, Germany) in 20 drug-naive FEP patients and 20 healthy control subjects (HC). Several clinical psychometric scales as well as neurocognitive tests were administered to all subjects in order to better define psychopatholog- ical status and vulnerability. EEG slow wave activity (SWA, spectral power between 1 and 4 Hz) and several slow wave parameters were computed at each electrode location, including density and amplitude, at each electrode location. Along with a group analysis between FEP and HC, a subgroup analysis was also computed between patients who showed a progression of symptoms to full-blown Schizophrenia (SCZ, n = 10) over the next 12-month follow-up and those who did not (OTH, n = 10). Results: Sleep macro-architecture was globally preserved in FEP patients. SWA (1–4 Hz) was lower in FEP compared to HC but this difference didn’t reach statistical significance. Slow wave density was decreased in FEP compared to HC, with a significance that survived multiple comparison correction over a large fronto-central cluster. Mean amplitude was pre- served. At the subgroup analysis, these results were largely driven by the subgroup of patients with a confirmed diagnosis of SCZ at a 12-month fol- low-up. Indeed, no difference could be found between OTH and HC, while a strong significance was still evident between SCZ and HC.",
"type": "NarrativeText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "5807689818fb4d4d7e7112bae842b50c",
"text": "S8. GRIN1 PROMOTER METHYLATION CHANGES IN BLOOD OF EARLY-ONSET PSYCHOTIC PATIENTS AND UNAFFECTED SIBLINGS WITH CHILDHOOD TRAUMA",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "59aa170fed2f7a1ab36e75f0cd0461c4",
"text": "Camila Loureiro*1, Corsi-Zuelli Fabiana1, Fachim Helene Aparecida1, Shuhama Rosana1, Menezes Paulo Rossi1, Dalton Caroline F2,",
"type": "UncategorizedText",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "3aa954bd1e29835edef83b7cd04e9769",
"text": "AQ3",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
},
{
"element_id": "574d62523bf0c0a56967c26c82840550",
"text": "SIRS 2020 Abstracts",
"type": "Title",
"metadata": {
"data_source": {},
"filetype": "application/pdf",
"page_number": 1
}
}
]

15
test_unstructured_ingest/test-ingest-biomed-api.sh
View File

@ -1,23 +1,11 @@
#!/usr/bin/env bash
# shellcheck disable=SC2317
# NOTE(crag): remove above shellcheck line when the biomed issue is fixed
echo "Skipping test-ingest-biomed-api.sh,"
echo "see https://github.com/Unstructured-IO/unstructured/issues/468"
echo
exit 0
set -e
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
cd "$SCRIPT_DIR"/.. || exit 1
if [[ "$CI" == "true" ]]; then
if [ "$(( RANDOM % 10))" -lt 1 ] ; then
echo "Skipping ingest 90% of biomed tests to avoid occaisonal ftp issue."
exit 0
fi
fi
if [[ "$(find test_unstructured_ingest/expected-structured-output/biomed-ingest-output-api/ -type f -size +10k | wc -l)" != 2 ]]; then
echo "The test fixtures in test_unstructured_ingest/expected-structured-output/biomed-ingest-output-api/ look suspicious. At least one of the files is too small."
echo "Did you overwrite test fixtures with bad outputs?"
@ -28,6 +16,9 @@ PYTHONPATH=. ./unstructured/ingest/main.py \
--metadata-exclude filename,file_directory,metadata.data_source.date_processed \
--biomed-api-from "2019-01-02" \
--biomed-api-until "2019-01-02+00:03:10" \
--biomed-max-retries 5 \
--biomed-max-request-time 30 \
--biomed-decay .3 \
--structured-output-dir biomed-ingest-output-api \
--num-processes 2 \
--partition-strategy hi_res \

15
test_unstructured_ingest/test-ingest-biomed-path.sh
View File

@ -1,23 +1,11 @@
#!/usr/bin/env bash
# shellcheck disable=SC2317
# NOTE(crag): remove above shellcheck line when the biomed issue is fixed
echo "Skipping test-ingest-biomed-path.sh,"
echo "see https://github.com/Unstructured-IO/unstructured/issues/468"
echo
exit 0
set -e
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
cd "$SCRIPT_DIR"/.. || exit 1
if [[ "$CI" == "true" ]]; then
if [ "$(( RANDOM % 10))" -lt 1 ] ; then
echo "Skipping ingest 90% of biomed tests to avoid the occaisonal ftp issue."
exit 0
fi
fi
if [[ "$(find test_unstructured_ingest/expected-structured-output/biomed-ingest-output-path/ -type f -size +10k | wc -l)" != 1 ]]; then
echo "The test fixtures in test_unstructured_ingest/expected-structured-output/biomed-ingest-output-path/ look suspicious. At least one of the files is too small."
echo "Did you overwrite test fixtures with bad outputs?"
@ -27,6 +15,9 @@ fi
PYTHONPATH=. ./unstructured/ingest/main.py \
--metadata-exclude filename,file_directory,metadata.data_source.date_processed \
--biomed-path "oa_pdf/07/07/sbaa031.073.PMC7234218.pdf" \
--biomed-max-retries 5 \
--biomed-max-request-time 30 \
--biomed-decay .3 \
--structured-output-dir biomed-ingest-output-path \
--num-processes 2 \
--partition-strategy hi_res \

2
unstructured/__version__.py
View File

@ -1 +1 @@
__version__ = "0.7.6-dev0" # pragma: no cover
__version__ = "0.7.6-dev1" # pragma: no cover

29
unstructured/ingest/connector/biomed.py
View File

@ -8,6 +8,8 @@ from typing import List, Union
import requests
from bs4 import BeautifulSoup
from requests.adapters import HTTPAdapter
from urllib3.util import Retry
from unstructured.ingest.interfaces import (
BaseConnector,
@ -43,6 +45,9 @@ class SimpleBiomedConfig(BaseConnectorConfig):
id_: str
from_: str
until: str
max_retries: int = 5
request_timeout: int = 45
decay: float = 0.3
def validate_api_inputs(self):
valid = False
@ -95,7 +100,9 @@ class SimpleBiomedConfig(BaseConnectorConfig):
elif "command successful" in response:
self.is_dir = True
else:
raise ValueError("Something went wrong when validating the path: {path}.")
raise ValueError(
"Something went wrong when validating the path: {path}.",
)
@dataclass
@ -148,7 +155,9 @@ class BiomedIngestDoc(BaseIngestDoc):
output_filename = self._output_filename()
output_filename.parent.mkdir(parents=True, exist_ok=True)
with open(output_filename, "w") as output_f:
output_f.write(json.dumps(self.isd_elems_no_filename, ensure_ascii=False, indent=2))
output_f.write(
json.dumps(self.isd_elems_no_filename, ensure_ascii=False, indent=2),
)
logger.info(f"Wrote {output_filename}")
@ -157,7 +166,11 @@ class BiomedConnector(BaseConnector):
config: SimpleBiomedConfig
def __init__(self, standard_config: StandardConnectorConfig, config: SimpleBiomedConfig):
def __init__(
self,
standard_config: StandardConnectorConfig,
config: SimpleBiomedConfig,
):
super().__init__(standard_config, config)
self.cleanup_files = (
not self.standard_config.preserve_downloads and not self.standard_config.download_only
@ -198,7 +211,15 @@ class BiomedConnector(BaseConnector):
endpoint_url += f"&until={self.config.until}"
while endpoint_url:
response = requests.get(endpoint_url)
session = requests.Session()
retries = Retry(
total=self.config.max_retries,
backoff_factor=self.config.decay,
)
adapter = HTTPAdapter(max_retries=retries)
session.mount("http://", adapter)
session.mount("https://", adapter)
response = session.get(endpoint_url, timeout=self.config.request_timeout)
soup = BeautifulSoup(response.content, features="lxml")
urls = [link["href"] for link in soup.find_all("link")]

21
unstructured/ingest/main.py
View File

@ -243,6 +243,21 @@ class MainProcess:
default=None,
help="Until parameter for OA Web Service API.",
)
@click.option(
"--biomed-max-retries",
default=1,
help="Max requests to OA Web Service API.",
)
@click.option(
"--biomed-max-request-time",
default=45,
help="(In seconds) Max request time to OA Web Service API.",
)
@click.option(
"--biomed-decay",
default=0.3,
help="(In float) Factor to multiply the delay between retries.",
)
@click.option(
"--wikipedia-page-title",
default=None,
@ -413,6 +428,9 @@ def main(
biomed_api_id,
biomed_api_from,
biomed_api_until,
biomed_max_retries,
biomed_max_request_time,
biomed_decay,
wikipedia_page_title,
wikipedia_auto_suggest,
github_url,
@ -720,6 +738,9 @@ def main(
id_=biomed_api_id,
from_=biomed_api_from,
until=biomed_api_until,
max_retries=biomed_max_retries,
request_timeout=biomed_max_request_time,
decay=biomed_decay,
),
)
elif local_input_path: